Search

The optimal scheduling of interfering links in a dense wireless network with full frequency reuse is a challenging task. The traditional method involves first estimating all the interfering channel strengths and then optimizing the scheduling based on the model. This model-based method is, however, resource intensive and computationally hard because channel estimation is expensive in dense networks; furthermore, finding even a locally optimal solution of the resulting optimization problem may be computationally complex. This paper shows that by using a deep learning approach, it is possible to bypass the channel estimation and to schedule links efficiently based solely on the geographic locations of the transmitters and the receivers due to the fact that in many propagation environments, the wireless channel strength is largely a function of the distance-dependent path-loss. This is accomplished by unsupervised training over randomly deployed networks and by using a novel neural network architecture that computes the geographic spatial convolutions of the interfering or interfered neighboring nodes along with subsequent multiple feedback stages to learn the optimum solution. The resulting neural network gives a near-optimal performance for sum-rate maximization and is capable of generalizing to larger deployment areas and to deployments of different link densities. Moreover, to provide fairness, this paper proposes a novel scheduling approach that utilizes the sum-rate optimal scheduling algorithm over judiciously chosen subsets of links for maximizing a proportional fairness objective over the network. The proposed approach shows highly competitive and generalizable network utility maximization results. [ABSTRACT FROM AUTHOR]

To convey neural network architectures in publications, appropriate visualizations are of great importance. While most current deep learning papers contain such visualizations, these are usually handcrafted just before publication, which results in a lack of a common visual grammar, significant time investment, errors, and ambiguities. Current automatic network visualization tools focus on debugging the network itself and are not ideal for generating publication visualizations. Therefore, we present an approach to automate this process by translating network architectures specified in Keras into visualizations that can directly be embedded into any publication. To do so, we propose a visual grammar for convolutional neural networks (CNNs), which has been derived from an analysis of such figures extracted from all ICCV and CVPR papers published between 2013 and 2019. The proposed grammar incorporates visual encoding, network layout, layer aggregation, and legend generation. We have further realized our approach in an online system available to the community, which we have evaluated through expert feedback, and a quantitative study. It not only reduces the time needed to generate network visualizations for publications, but also enables a unified and unambiguous visualization design. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $\Pi$ Π -Nets, a new class of function approximators based on polynomial expansions. $\Pi$ Π -Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that $\Pi$ Π -Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, $\Pi$ Π -Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets. [ABSTRACT FROM AUTHOR]

A general deep learning (DL) mechanism for a multiple hidden layer feed-forward neural network contains two parts, i.e., 1) an unsupervised greedy layer-wise training and 2) a supervised fine-tuning which is usually an iterative process. Although this mechanism has been demonstrated in many fields to be able to significantly improve the generalization of neural network, there is no clear evidence to show which one of the two parts plays the essential role for the generalization improvement, resulting in an argument within the DL community. Focusing on this argument, this paper proposes a new DL approach to train multilayer feed-forward neural networks. This approach uses restricted Boltzmann machine (RBM) as the layer-wise training and uses the generalized inverse of a matrix as the supervised fine-tuning. Different from the general deep training mechanism like back-propagation (BP), the proposed approach does not need to iteratively tune the weights, and therefore, has many advantages such as quick training, better generalization, and high understandability, etc. Experimentally, the proposed approach demonstrates an excellent performance in comparison with BP-based DL and the traditional training method for multilayer random weight neural networks. To a great extent, this paper demonstrates that the supervised part plays a more important role than the unsupervised part in DL, which provides some new viewpoints for exploring the essence of DL. [ABSTRACT FROM AUTHOR]

This paper investigates a deep reinforcement learning (DRL)-based MAC protocol for heterogeneous wireless networking, referred to as a Deep-reinforcement Learning Multiple Access (DLMA). Specifically, we consider the scenario of a number of networks operating different MAC protocols trying to access the time slots of a common wireless medium. A key challenge in our problem formulation is that we assume our DLMA network does not know the operating principles of the MACs of the other networks—i.e., DLMA does not know how the other MACs make decisions on when to transmit and when not to. The goal of DLMA is to be able to learn an optimal channel access strategy to achieve a certain pre-specified global objective. Possible objectives include maximizing the sum throughput and maximizing $\alpha $ -fairness among all networks. The underpinning learning process of DLMA is based on DRL. With proper definitions of the state space, action space, and rewards in DRL, we show that DLMA can easily maximize the sum throughput by judiciously selecting certain time slots to transmit. Maximizing general $\alpha $ -fairness, however, is beyond the means of the conventional reinforcement learning (RL) framework. We put forth a new multi-dimensional RL framework that enables DLMA to maximize general $\alpha $ -fairness. Our extensive simulation results show that DLMA can maximize sum throughput or achieve proportional fairness (two special classes of $\alpha $ -fairness) when coexisting with TDMA and ALOHA MAC protocols without knowing they are TDMA or ALOHA. Importantly, we show the merit of incorporating the use of neural networks into the RL framework (i.e., why DRL and not just traditional RL): specifically, the use of DRL allows DLMA (i) to learn the optimal strategy with much faster speed and (ii) to be more robust in that it can still learn a near-optimal strategy even when the parameters in the RL framework are not optimally set. [ABSTRACT FROM AUTHOR]

Despite encouraging results have been achieved in human pose estimation in recent years, it remains challenging problems. When the background is similar to the human body parts, and there are small persons with low-resolution in the image, the performance may degrade dramatically. This paper addresses problems in background-inference and small-person pose estimation. To achieve this, a novel pose estimation algorithm is proposed on the basis of person semantic segmentation deep neural network. Different from most previous methods with a single pose estimation model, we generate mixture models with pose estimation and semantic segmentation. We introduce novel generative adversarial model and auxiliary model to realize the semantic segmentation network, which can handle the confusion of the similar regions in the background. In addition, to address the problem of the scale differences between big and small persons’ keypoints, we add additional position and channel attention modules to the first two stages of OpenPose. We conduct extensive experiments on COCO and VOC datasets. And we compare the proposed method with the most popular state-of-the-art human pose estimation and semantic segmentation frameworks, including MultiPoseNet, Deterton2 and DeepLab V3. Our experimental results show that the proposed method is more accurate than the state-of-the-art algorithms and performs effectively in tackling the complex situations. [ABSTRACT FROM AUTHOR]

Stereo matching methods consist of matching cost computation and several post processing steps. Deep learning methods have greatly raised the accuracy of matching cost and achieved the lowest error rate on several public datasets. However, their generality capabilities are not the best due to potential overfitting, which is the common problem of supervised learning approaches. This paper proposes a convolutional neural network (CNN) based cost estimation method for computing the similarity of image patches. In consideration of accuracy and generalization capability, small size convolution kernels are chosen in the convolution layer and dropout in the decision layer is used for preventing overfitting. After obtaining stereo matching cost from the output of the CNN, several post-processing operations are adopted for disparity optimization, which includes semi-global matching in 1-D from different directions, a left-right consistency check, and the slanted plane smoothing method. The method is evaluated on KITTI 2012, KITTI 2015, and Middlebury stereo datasets and the experimental results on the KITTI benchmark demonstrate the competitive accuracy performance of the approach. Additionally, to test the generalization of the method, a series of extended crossover experiments are conducted in which the training samples and testing samples come from different datasets. The results indicate superior generalization capability of our method than other supervised learning methods. [ABSTRACT FROM AUTHOR]

This paper presents a scalable inference accelerator called a deep-learning specific instruction-set processor (DSIP) to support various convolutional neural networks (CNNs). For CNNs requiring a large amount of computations and memory accesses, a programmable inference system called master–slave instruction set architecture (ISA) is newly proposed to achieve high flexibility, processing speed, and energy efficiency. The master is responsible for sending and receiving feature maps in order to deal with neural networks in a scalable way, and the slave performs CNN operations, such as multiply accumulate, max pooling, and activation functions, on the features received from the master. The master–slave ISA maximizes computation speed by overlapping the off-chip data transmission and the CNN operations, and reduces power consumption by performing the convolution incrementally to reuse input and partial-sum data as maximally as possible. An inference system can be configured by connecting multiple DSIPs in a form of either 1-D or 2-D chain structure in order to enhance computation speed further. To evaluate the proposed accelerator, a prototype chip is implemented and evaluated for AlexNet. Compared to the state-of-the-art accelerator, the DSIP-based system enhances the energy efficiency by 2.17 $\times $ . [ABSTRACT FROM AUTHOR]

In this paper, we experimentally and analytically evaluate the reliability of two state-of-the-art neural networks for linear regression and pattern recognition (multilayer perceptron and single-layer perceptron) implemented in a system-on-chip composed of a field-programmable gate array (FPGA) and a microprocessor. We have considered, for each neural network, three different activation function complexities, to evaluate how the implementation affects FPGAs reliability. As we show in this paper, higher complexity increases the exposed area but reduces the probability of one failure to impact the network output. In addition, we propose to distinguish between critical and tolerable errors in artificial neural networks. Experiments using a controlled heavy-ions beam show that, for both networks, only about 30% of the observed output errors actually affect the outputs correctness. We identify the causes of critical errors through fault injection, and found that faults in initial layers are more likely to significantly affect the output. [ABSTRACT FROM PUBLISHER]

Recent studies have shown that a Deep Convolutional Neural Network (DCNN) trained on a large image dataset can be used as a universal image descriptor and that doing so leads to impressive performance for a variety of image recognition tasks. Most of these studies adopt activations from a single DCNN layer, usually a fully-connected layer, as the image representation. In this paper, we proposed a novel way to extract image representations from two consecutive convolutional layers: one layer is used for local feature extraction and the other serves as guidance to pool the extracted features. By taking different viewpoints of convolutional layers, we further develop two schemes to realize this idea. The first directly uses convolutional layers from a DCNN. The second applies the pre-trained CNN on densely sampled image regions and treats the fully-connected activations of each image region as a convolutional layer's feature activations. We then train another convolutional layer on top of that as the pooling-guidance convolutional layer. By applying our method to three popular visual classification tasks, we find that our first scheme tends to perform better on applications which demand strong discrimination on lower-level visual patterns while the latter excels in cases that require discrimination on category-level patterns. Overall, the proposed method achieves superior performance over existing approaches for extracting image representations from a DCNN. In addition, we apply cross-layer pooling to the problem of image retrieval and propose schemes to reduce the computational cost. Experimental results suggest that the proposed method achieves promising results for the image retrieval task. [ABSTRACT FROM AUTHOR]

The key role of spectrum sensing in cognitive radios attracted substantial research attention to improve the performance of detectors. We consider a general model for the receiver noise with the potential of generalization towards modeling noise in various environments. This general noise model describes accurately noise characteristics ranging from the Gaussian noise to the severe impulsive noise. However, many previous studies are based on the ideal Gaussian noise, and they cannot capture the non-Gaussian models. To provide a robust detector against different behaviors of the noise in various environments, we employ a convolutional neural network (CNN) compatible with different noise models. The proposed CNN detector is data-driven, and due to its single-dimensional input layer, it is consistent with the received signal and requires no pre-processing. The likelihood ratio test (LRT), the Wald, and the Rao tests for this problem are derived to enrich the paper with comparative evaluations of the proposed CNN and conventional model-based approaches and other neural networks. Although various simulated scenarios substantiate the general superiority and robustness of the CNN-based against impulsive noise and mismatch of parameters, it requires higher computational complexity than other discussed detectors. [ABSTRACT FROM AUTHOR]

Mobile sensing is a promising sensing paradigm in the era of Internet of Things (IoT) that utilizes mobile device sensors to collect sensory data about sensing targets and further applies learning techniques to recognize the sensed targets to correct classes or categories. Due to the recent great success of deep learning, an emerging trend is to adopt deep learning in this recognition process, while we find an overlooked yet crucial issue to be solved in this paper — The size of deep learning models should be sufficiently large for reliably classifying various types of recognition targets, while the achieved processing delay may fail to satisfy the stringent latency requirement from applications. If we blindly shrink the deep learning model for acceleration, the performance cannot be guaranteed. To cope with this challenge, this paper presents a compact deep neural network architecture, namely cDeepArch. The key idea of the cDeepArch design is to decompose the entire recognition task into two lightweight sub-problems: context recognition and the context-oriented target recognitions. This decomposition essentially utilizes the adequate storage to trade for the CPU and memory resource consumptions during execution. In addition, we further formulate the execution latency for decomposed deep learning models and propose a set of enhancement techniques, so that system performance and resource consumption can be quantitatively balanced. We implement a cDeepArch prototype system and conduct extensive experiments. The result shows that cDeepArch achieves excellent recognition performance and the execution latency is also lightweight. [ABSTRACT FROM AUTHOR]

Residual networks (ResNets) have introduced a milestone for the deep learning community due to their outstanding performance in diverse applications. They enable efficient training of increasingly deep networks, reducing the training difficulty and error. The main intuition behind them is that, instead of mapping the input information, they are mapping a residual part of it. Since the original work, a lot of extensions have been proposed to improve information mapping. In this paper, a novel extension of the residual block is proposed inspired by linear dynamical systems (LDSs), called LDS-ResNet. Specifically, a new module is presented that improves mapping of residual information by transforming it in a hidden state and then mapping it back to the desired feature space using convolutional layers. The proposed module is utilized to construct multi-branch residual blocks for convolutional neural networks. An exploration of possible architectural choices is presented and evaluated. Experimental results show that LDS-ResNet outperforms the original ResNet in image classification and object detection tasks on public datasets such as CIFAR-10/100, ImageNet, VOC, and MOT2017. Moreover, its performance boost is complementary to other extensions of the original network such as pre-activation and bottleneck, as well as stochastic training and Squeeze-Excitation. [ABSTRACT FROM AUTHOR]

Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using adversarial-based and perceptual losses to improve the performance on various image restoration tasks; however, these have yet to be applied for video super-resolution. In this paper, we propose a generative adversarial network (GAN)-based formulation for VSR. We introduce a new generator network optimized for the VSR problem, named VSRResNet, along with new discriminator architecture to properly guide VSRResNet during the GAN training. We further enhance our VSR GAN formulation with two regularizers, a distance loss in feature-space and pixel-space, to obtain our final VSRResFeatGAN model. We show that pre-training our generator with the mean-squared-error loss only quantitatively surpasses the current state-of-the-art VSR models. Finally, we employ the PercepDist metric to compare the state-of-the-art VSR models. We show that this metric more accurately evaluates the perceptual quality of SR solutions obtained from neural networks, compared with the commonly used PSNR/SSIM metrics. Finally, we show that our proposed model, the VSRResFeatGAN model, outperforms the current state-of-the-art SR models, both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. [ABSTRACT FROM AUTHOR]

Independent component analysis (ICA) is a statistical method for transforming an observable multi-dimensional random vector into components that are as statistically independent as possible from each other. Usually, the ICA framework assumes a model according to which the observations are generated (such as a linear transformation with additive noise). ICA over finite fields is a special case of ICA in which both the observations and the independent components are over a finite alphabet. In this paper, we consider a generalization of this framework in which an observation vector is decomposed to its independent components (as much as possible) with no prior assumption on the way it was generated. This generalization is also known as Barlow’s minimal redundancy representation problem and is considered an open problem. We propose several theorems and show that this hard problem can be accurately solved with a branch and bound search tree algorithm, or tightly approximated with a series of linear problems. Our contribution provides the first efficient set of solutions to Barlow’s problem. The minimal redundancy representation (also known as factorial code) has many applications, mainly in the fields of neural networks and deep learning. The binary ICA is also shown to have applications in several domains, including medical diagnosis, multi-cluster assignment, network tomography, and internet resource management. In this paper, we show that this formulation further applies to multiple disciplines in source coding, such as predictive coding, distributed source coding, and coding of large alphabet sources. [ABSTRACT FROM AUTHOR]

The high voltage insulator requires continuous monitoring and inspection to prevent failures and emergencies. Manual inspections are costly as it requires covering a large geographical area where insulators are often subjected to harsh weather conditions. Automatic detection of insulators from aerial images is the first step towards performing real-time classification of insulator conditions using Unmanned Aerial Vehicle (UAV). In this paper, we provide a cost-effective solution for detecting insulators under the conditions of an uncluttered background, varied object resolution and illumination conditions using You Only Look Once (YOLO) deep learning neural network model from aerial images. We apply data augmentation to avoid overfitting with a training set size of 56000 image samples. It is demonstrated experimentally that this method can accurately locate insulator on UAV based real-time image data. The detected insulator images are then successfully subjected to insulator surface condition assessment for the presence of ice, snow and water using different classifiers. [ABSTRACT FROM AUTHOR]

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse-view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U-Net variants such as dual frame and tight frame U-Nets satisfy the so-called frame condition which makes them better for effective recovery of high frequency edges in sparse-view CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance. [ABSTRACT FROM AUTHOR]

In this paper, we study the challenging problem of categorizing videos according to high-level semantics such as the existence of a particular human action or a complex event. Although extensive efforts have been devoted in recent years, most existing works combined multiple video features using simple fusion strategies and neglected the utilization of inter-class semantic relationships. This paper proposes a novel unified framework that jointly exploits the feature relationships and the class relationships for improved categorization performance. Specifically, these two types of relationships are estimated and utilized by imposing regularizations in the learning process of a deep neural network (DNN). Through arming the DNN with better capability of harnessing both the feature and the class relationships, the proposed regularized DNN (rDNN) is more suitable for modeling video semantics. We show that rDNN produces better performance over several state-of-the-art approaches. Competitive results are reported on the well-known Hollywood2 and Columbia Consumer Video benchmarks. In addition, to stimulate future research on large scale video categorization, we collect and release a new benchmark dataset, called FCVID, which contains 91,223 Internet videos and 239 manually annotated categories. [ABSTRACT FROM PUBLISHER]

Error disagreement-based active learning (AL) selects the data that maximally update the error of a classification hypothesis. However, poor human supervision (e.g., few labels, improper classifier parameters) may weaken or clutter this update; moreover, the computational cost of performing a greedy search to estimate the errors using a deep neural network is intolerable. In this paper, a novel disagreement coefficient based on distribution, not error, provides a tighter bound on label complexity, which further guarantees its generalization in hyperbolic space. The focal points derived from the squared Lorentzian distance, present more effective hyperbolic representations on aspherical distribution from geometry, replacing the typical euclidean, kernelized, and Poincaré centroids. Experiments on different deep AL tasks show that, the focal representation adopted in a tree-likeliness splitting, significantly performs better than typical baselines of centroid representations and error disagreement, and state-of-the-art neural network architectures-based AL, dramatically accelerating the learning process. [ABSTRACT FROM AUTHOR]

With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed, or abused without respecting the intellectual properties of legitimate owners. Following recent progresses along this line, we investigate a number of watermark-based DNN ownership verification methods in the face of ambiguity attacks, which aim to cast doubts on the ownership verification by forging counterfeit watermarks. It is shown that ambiguity attacks pose serious threats to existing DNN watermarking methods. As remedies to the above-mentioned loophole, this paper proposes novel passport-based DNN ownership verification schemes which are both robust to network modifications and resilient to ambiguity attacks. The gist of embedding digital passports is to design and train DNN models in a way such that, the DNN inference performance of an original task will be significantly deteriorated due to forged passports. In other words, genuine passports are not only verified by looking for the predefined signatures, but also reasserted by the unyielding DNN model inference performances. Extensive experimental results justify the effectiveness of the proposed passport-based DNN ownership verification schemes. Code is available at https://github.com/kamwoh/DeepIPR. [ABSTRACT FROM AUTHOR]

Most studies about deep learning are based on neural network models, where many layers of parameterized nonlinear differentiable modules are trained by backpropagation. Recently, it has been shown that deep learning can also be realized by non-differentiable modules without backpropagation training called deep forest. We identify that deep forest has high time costs and memory requirements—this has inhibited its use on large-scale datasets. In this paper, we propose a simple and effective approach with three main strategies for efficient learning of deep forest. First, it substantially reduces the number of instances that needs to be processed through redirecting instances having high predictive confidence straight to the final level for prediction, by-passing all the intermediate levels. Second, many non-informative features are screened out, and only the informative ones are used for learning at each level. Third, an unsupervised feature transformation procedure is proposed to replace the supervised multi-grained scanning procedure. Our theoretical analysis supports the proposed approach in varying the model complexity from low to high as the number of levels increases in deep forest. Experiments show that our approach achieves highly competitive predictive performance with reduced time cost and memory requirement by one to two orders of magnitude. [ABSTRACT FROM AUTHOR]

The efficiency of link adaptation in wireless communications relies greatly on the accuracy of channel knowledge and transmission mode selection. In this paper, a novel deep learning based link adaptation framework is proposed for the orthogonal frequency-division multiplexing (OFDM) systems with compressed-sensing-assisted index modulation, termed as OFDM-CSIM, communicating over millimeter-wave (mmWave) channels. To achieve link adaptation, a novel multi-layer sparse Bayesian learning (SBL) algorithm is proposed for accurately and instantaneously providing the required channel state information. Meanwhile, a deep neural networks (DNN)-assisted adaptive modulation algorithm is proposed to choose the best possible transmission mode to maximize the achievable throughput. Simulation results show that the proposed multi-layer SBL algorithm enables more accurate channel estimation than the conventional techniques. The DNN-based adaptive modulator is capable of achieving a higher throughput than the learning-assisted solution based on the $k$ nearest neighbor ($k$ -NN) algorithm, and also the classic average signal-to-noise ratio (SNR)-based solutions. Moreover, analysis shows that both the multi-layer SBL algorithm and the DNN-assisted adaptive modulator achieve better performance than their respective conventional counterparts while at a significantly lower computational complexity cost. [ABSTRACT FROM AUTHOR]

The light field (LF) reconstruction is mainly confronted with two challenges, large disparity and the non-Lambertian effect. Typical approaches either address the large disparity challenge using depth estimation followed by view synthesis or eschew explicit depth information to enable non-Lambertian rendering, but rarely solve both challenges in a unified framework. In this paper, we revisit the classic LF rendering framework to address both challenges by incorporating it with advanced deep learning techniques. First, we analytically show that the essential issue behind the large disparity and non-Lambertian challenges is the aliasing problem. Classic LF rendering approaches typically mitigate the aliasing with a reconstruction filter in the Fourier domain, which is, however, intractable to implement within a deep learning pipeline. Instead, we introduce an alternative framework to perform anti-aliasing reconstruction in the image domain and analytically show comparable efficacy on the aliasing issue. To explore the full potential, we then embed the anti-aliasing framework into a deep neural network through the design of an integrated architecture and trainable parameters. The network is trained through end-to-end optimization using a peculiar training set, including regular LFs and unstructured LFs. The proposed deep learning pipeline shows a substantial superiority in solving both the large disparity and the non-Lambertian challenges compared with other state-of-the-art approaches. In addition to the view interpolation for an LF, we also show that the proposed pipeline also benefits light field view extrapolation. [ABSTRACT FROM AUTHOR]

With the popularity of location-aware devices (e.g., smart phones), large amounts of location-based social media data such as check-ins are generated. This stimulates plenty of studies for POI recommendations by applying machine learning techniques. However, most of the existing studies focus on POI recommendations in the same city or region, and fail to recommend POIs for users when they travel to a new city. In this paper, we propose a novel deep neural network, named as ST-TransRec, for crossing-city POI recommendations. It integrates the deep neural network, transfer learning technique, and density-based resampling method into a unified framework. In this model, the deep neural network is used to capture users’ preferences for POIs and learn the embeddings of POIs. Besides, the transfer learning technique is employed to bridge the gap between cities that results from the city-dependent features. As the distributions over POIs are imbalanced, we design a density-based spatial resampling model which enables POIs to be well matched across cities. We conduct extensive experiments on two real-world datasets. The experimental results show the advantages of ST-TransRec over the state-of-the-art methods for crossing-city POI recommendations. [ABSTRACT FROM AUTHOR]

Rear-end collision prediction has gained an increasing attention for safety improvement in smart cities. It is urgent to design efficient warning strategies for rear-end collisions which is one of the main causes of traffic accidents. The existing researches have been conducted to predict the collisions. Learning-based methods are proposed to solve this complicated issue, which the traditional methods are difficult to solve. However, due to some limitations in terms of the feature extraction and prediction performance, back-propagation learning methods are facing challenge. In this paper, we proposed a novel Rear-end Collision Prediction Mechanism with deep learning method (RCPM), in which a convolutional neural network model is established. In RCPM, the dataset is smoothed and expanded based on genetic theory to alleviate the class imbalance problem. The preprocessed dataset is divided into training and testing sets as the input to train our convolutional neural network model. The experimental results show that compared with the Honda, Berkeley and multi-layer perception neural-network-based algorithms, RCPM effectively improves performance to predict rear-end collisions. [ABSTRACT FROM AUTHOR]

Despite the promise of recent deep neural networks to provide more accurate and efficient iris recognition compared to traditional techniques, there are vital properties of the classic IrisCode which are almost unable to be achieved with current deep iris networks: the compactness of model and the small number of computing operations (FLOPs). This paper casts the iris network design process as a constrained optimization problem which takes model size and computation into account as learning criteria. On one hand, this allows us to fully automate the network design process to search for the optimal iris network architecture with the highest recognition accuracy confined to the computation and model compactness constraints. On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent deep iris networks. It also enables us to learn an optimal iris network and demonstrate state-of-the-art performance with less computation and memory requirements. [ABSTRACT FROM AUTHOR]

Frequency filtering is widely used in routine processing of seismic data to improve the signal-to-noise ratio (SNR) of recorded signals and by doing so to improve subsequent analyses. In this paper, we develop a new denoising/decomposition method, DeepDenoiser, based on a deep neural network. This network is able to simultaneously learn a sparse representation of data in the time–frequency domain and a non-linear function that maps this representation into masks that decompose input data into a signal of interest and noise (defined as any non-seismic signal). We show that DeepDenoiser achieves impressive denoising of seismic signals even when the signal and noise share a common frequency band. Because the noise statistics are automatically learned from data and require no assumptions, our method properly handles white noise, a variety of colored noise, and non-earthquake signals. DeepDenoiser can significantly improve the SNR with minimal changes in the waveform shape of interest, even in the presence of high noise levels. We demonstrate the effect of our method on improving earthquake detection. There are clear applications of DeepDenoiser to seismic imaging, micro-seismic monitoring, and preprocessing of ambient noise data. We also note that the potential applications of our approach are not limited to these applications or even to earthquake data and that our approach can be adapted to diverse signals and applications in other settings. [ABSTRACT FROM AUTHOR]

Semantic segmentation methods based on deep neural networks have achieved great success in recent years. However, training such deep neural networks relies heavily on a large number of images with accurate pixel-level labels, which requires a huge amount of human effort, especially for large-scale remote sensing images. In this paper, we propose a point-based weakly supervised learning framework called the deep bilateral filtering network (DBFNet) for the semantic segmentation of remote sensing images. Compared with pixel-level labels, point annotations are usually sparse and cannot reveal the complete structure of the objects; they also lack boundary information, thus resulting in incomplete prediction within the object and the loss of object boundaries. To address these problems, we incorporate the bilateral filtering technique into deeply learned representations in two respects. First, since a target object contains smooth regions that always belong to the same category, we perform deep bilateral filtering (DBF) to filter the deep features by a nonlinear combination of nearby feature values, which encourages the nearby and similar features to become closer, thus achieving a consistent prediction in the smooth region. In addition, the DBF can distinguish the boundary by enlarging the distance between the features on different sides of the edge, thus preserving the boundary information well. Experimental results on two widely used datasets, the ISPRS 2-D semantic labeling Potsdam and Vaihingen datasets, demonstrate that our proposed DBFNet can achieve a highly competitive performance compared with state-of-the-art fully-supervised methods. Code is available at https://github.com/Luffy03/DBFNet. [ABSTRACT FROM AUTHOR]

Obstructive sleep apnea (OSA) is a chronic and prevalent condition with well-established comorbidities. However, many severe cases remain undiagnosed due to poor access to polysomnography (PSG), the gold standard for Obstructive sleep apnea (OSA) diagnosis. Accurate home-based methods to screen for OSA are needed, which can be applied inexpensively to high-risk subjects to identify those that require PSG to fully assess their condition. A number of methods that analyse speech or breathing sounds to screen for OSA have been previously investigated. However, these methods have constraints that limit their use in home environments (e.g., they require specialised equipment, are not robust to background noise, are obtrusive or depend on tightly controlled conditions). This paper proposes a novel method to screen for OSA, which analyses sleep breathing sounds recorded with a smartphone at home. Audio recordings made over a whole night are divided into segments, each of which is classified for the presence or absence of OSA by a deep neural network. The apnea-hypopnea index estimated from the segments predicted as containing evidence of OSA is then used to screen for the condition. Audio recordings made during home sleep apnea testing from 103 participants for 1 or 2 nights were used to develop and evaluate the proposed system. When screening for moderate OSA the acoustics based system achieved a sensitivity of 0.79 and a specificity of 0.80. The sensitivity and specificity when screening for severe OSA were 0.78 and 0.93, respectively. The system is suitable for implementation on consumer smartphones. [ABSTRACT FROM AUTHOR]

In general, an image attribute is a human-nameable visual property that has a semantic connotation. Appropriate modeling of the intrinsic contextual correlations among attributes plays a fundamental role in attribute detection. In this paper, we consider image attribute detection from the perspective of regularized deep learning. In particular, we propose a regularized deep belief network (rDBN) to perform the image attribute detection task, which is composed of two parts: 1) a detection DBN (dDBN) that models the joint distribution of images and their corresponding attributes, which acts as an attribute detector and 2) a contextual restricted Boltzmann machine that explicitly models the correlations among attributes acting as a regularizer that restraints the output detection result given by the dDBN to meet the contextual prior of attributes. Furthermore, we propose an efficient fine-tuning scheme that can further optimize the performance of the dDBN by backpropagation. Experimental results show that the proposed rDBN obtains improvements over the state-of-the-art methods for attribute detection on the benchmark data sets. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a discriminative representation for patterned fabric defect detection when only limited negative samples are available. Fabric patches are efficiently classified into defectless and defective categories by Fisher criterion-based stacked denoising autoencoders (FCSDA). First, fabric images are divided into patches of the same size, and both defective and defectless samples are utilized to train FCSDA. Second, test patches are classified through FCSDA into defective and defectless categories. Finally, the residual between the reconstructed image and defective patch is calculated, and the defect is located by thresholding. Experimental results demonstrate the effectiveness of the proposed scheme in the defect detection for periodic patterned fabric and more complex jacquard warp-knitted fabric. [ABSTRACT FROM AUTHOR]

While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, subsequent tasks that involve inference, reasoning, and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, it is naturally desirable to tightly integrate deep learning and Bayesian models within a principled probabilistic framework, which we call Bayesian deep learning. In this unified framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in return, the feedback from the inference process is able to enhance the perception of text or images. This paper proposes a general framework for Bayesian deep learning and reviews its recent applications on recommender systems, topic models, and control. In this paper, we also discuss the relationship and differences between Bayesian deep learning and other related topics such as the Bayesian treatment of neural networks. [ABSTRACT FROM PUBLISHER]

This paper deals with the use of emerging deep learning techniques in future wireless communication networks. It will be shown that the data-driven approaches should not replace, but rather complement, traditional design techniques based on mathematical models. Extensive motivation is given for why deep learning based on artificial neural networks will be an indispensable tool for the design and operation of future wireless communication networks, and our vision of how artificial neural networks should be integrated into the architecture of future wireless communication networks is presented. A thorough description of deep learning methodologies is provided, starting with the general machine learning paradigm, followed by a more in-depth discussion about deep learning and artificial neural networks, covering the most widely used artificial neural network architectures and their training methods. Deep learning will also be connected to other major learning frameworks, such as reinforcement learning and transfer learning. A thorough survey of the literature on deep learning for wireless communication networks is provided, followed by a detailed description of several novel case studies wherein the use of deep learning proves extremely useful for network design. For each case study, it will be shown how the use of (even approximate) mathematical models can significantly reduce the amount of live data that needs to be acquired/measured to implement the data-driven approaches. Finally, concluding remarks describe those that, in our opinion, are the major directions for future research in this field. [ABSTRACT FROM AUTHOR]

Recently, deep learning techniques have substantially boosted the performance of salient object detection in still images. However, the salient object detection in videos by using traditional handcrafted features or deep learning features is not fully investigated, probably due to the lack of sufficient manually labeled video data for saliency modeling, especially for the data-driven deep learning. This paper proposes a novel weakly supervised approach to the salient object detection in a video, which can learn a robust saliency prediction model by using very limited manually labeled data and a large amount of weakly labeled data that could be easily generated in a supervised approach. Furthermore, we propose a spatiotemporal cascade neural network architecture for saliency modeling, in which two fully convolutional networks are cascaded to evaluate the visual saliency from both spatial and temporal cues to lead the optimal video saliency prediction. The proposed approach is extensively evaluated on the widely used challenging data sets, and the experiments demonstrate that our proposed approach substantially outperforms the state-of-the-art salient object detection models. [ABSTRACT FROM AUTHOR]

A number of visual tracking methods achieve the state-of-the-art performance based on deep learning recently. However, most of these trackers utilize the deep neural network in regression task or classification task separately. In this paper, we propose an adversarial deep tracking framework. The framework is composed of a fully convolutional Siamese neural network (regression network) and a discriminative classification network. Then, we jointly optimize the regression network and the classification network by adversarial learning. In the uniform framework, the regression network and classification network can be trained end-to-end as a whole using large amounts of video training data sets. During the testing phase, the regression network generates a response map which reflects the location and the size of the target within each candidate search patch, and the classification network discriminates which response map is the best in terms of the corresponding template patch and candidate search patch. In addition, we propose an attention visualization algorithm for our tracker, and it reflects the area that attracts the attention of our tracker during tracking. The experimental results on three large-scale visual tracking benchmarks (OTB-100, TC-128, and VOT2016) demonstrate the effectiveness of the proposed tracking algorithm and show that our tracker performs comparably against the state-of-the-art trackers. [ABSTRACT FROM AUTHOR]

In this paper, we propose a deep convolutional neural network (DCNN) architecture that addresses the problem of video/image concept annotation by exploiting concept relations at two different levels. At the first level, we build on ideas from multi-task learning, and propose an approach to learn concept-specific representations that are sparse, linear combinations of representations of latent concepts. By enforcing the sharing of the latent concept representations, we exploit the implicit relations between the target concepts. At a second level, we build on ideas from structured output learning and propose the introduction, at training time, of a new cost term that explicitly models the correlations between the concepts. By doing so, we explicitly model the structure in the output space (i.e., the concept labels). Both of the above are implemented using standard convolutional layers and are incorporated in a single DCNN architecture that can then be trained end-to-end with standard back-propagation. Experiments on four large-scale video and image data sets show that the proposed DCNN improves concept annotation accuracy and outperforms the related state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Effective network slicing requires an infrastructure/network provider to deal with the uncertain demands and real-time dynamics of the network resource requests. Another challenge is the combinatorial optimization of numerous resources, e.g., radio, computing, and storage. This paper develops an optimal and fast real-time resource slicing framework that maximizes the long-term return of the network provider while taking into account the uncertainty of resource demands from tenants. Specifically, we first propose a novel system model that enables the network provider to effectively slice various types of resources to different classes of users under separate virtual slices. We then capture the real-time arrival of slice requests by a semi-Markov decision process. To obtain the optimal resource allocation policy under the dynamics of slicing requests, e.g., uncertain service time and resource demands, a Q-learning algorithm is often adopted in the literature. However, such an algorithm is notorious for its slow convergence, especially for problems with large state/action spaces. This makes Q-learning practically inapplicable to our case, in which multiple resources are simultaneously optimized. To tackle it, we propose a novel network slicing approach with an advanced deep learning architecture, called deep dueling, that attains the optimal average reward much faster than the conventional Q-learning algorithm. This property is especially desirable to cope with the real-time resource requests and the dynamic demands of the users. Extensive simulations show that the proposed framework yields up to 40% higher long-term average return while being few thousand times faster, compared with the state-of-the-art network slicing approaches. [ABSTRACT FROM AUTHOR]

Large-scale matrix-vector multiplications, which dominate in deep neural networks (DNNs), are limited by data movement in modern VLSI technologies. This paper addresses data movement via an in-memory-computing accelerator that employs charged-domain mixed-signal operation for enhancing compute SNR and, thus, scalability. The architecture supports analog/binary input activation (IA)/weight first layer (FL) and binary/binary IA/weight hidden layers (HLs), with batch normalization and input–output (IO) (buffering) circuitry to enable cascading, if desired, for realizing different DNN layers. The architecture is arranged as $8\times 8=64$ in-memory-computing neuron tiles, supporting up to 512, $3\times 3\times 512$ -input HL neurons and 64, $3\times 3\times 3$ -input FL neurons, configurable via tile-level clock gating. In-memory computing is achieved using an 8T bit cell with overlaying metal-oxide-metal (MOM) capacitor, yielding a structure having $1.8\times $ the area of a standard 6T bit cell. Implemented in 65-nm CMOS, the design achieves HLs/FL energy efficiency of 866/1.25 TOPS/W and throughput of 18876/43.2 GOPS (1498/3.43 GOPS/mm2), when implementing convolution layers; and 658/0.95 TOPS/W, 9438/10.47 GOPS (749/0.83 GOPS/mm2), when implementing convolution followed by batch normalization layers. Several large-scale neural networks are demonstrated, showing performance on standard benchmarks (MNIST, CIFAR-10, and SVHN) equivalent to ideal digital computing. [ABSTRACT FROM AUTHOR]

This paper proposes a method for vehicle driving behavior recognition based on a six-axis motion processor. This method uses deep-learning technology to learn the sample data collected by the on-board sensor. To solve the problem of small sample size and easy overfitting, we propose a joint data augmentation (JDA) scheme, and design a new multi-view convolutional neural network model (MV-CNN). The JDA includes the multi-axis weighted fusion algorithm, background noise fusion algorithm, and random cropping algorithm to construct a sample dataset that is more in line with a complex real driving environment. With the CNN model, the direction of information propagation improved, and a new MV-CNN model was developed for the training, learning, and recognition of driving behavior. The performance of MV-CNN is experimentally compared with CNN, recurrent neural networks (RNN), LSTM, CNN+LSTM, and three-dimensional CNN. The results show that MV-CNN can obtain the best recall, precision, and F1-score. At the same time, MV-CNN and JDA have better generalization ability, reduce the training variance and deviation, and increase the stability of the model training process. [ABSTRACT FROM AUTHOR]

The GPS trajectories are rich with potential information that could be used to explore the regulation of traffic to serve the public. While that past approaches for short-term traffic prediction have existed for some time, emerging smart transportation technologies require the traffic prediction capability to be both fast and scalable to full urban networks. In this paper, we propose a novel neural network, named L-CNN based on CNN and LSTM, and develop an effective real-time prediction model to forecast the most likely potential passenger for taxi drivers. It is noteworthy that our model can be easily extended to other real-time traffic prediction problems, such as road traffic and flow prediction. Finally, we test our method based on GPS trajectories generated by Cheng Du taxi. The method presented provides passenger prediction over 15-min intervals for up to 1 h in advance and the results prove the efficiency of our predicting system. [ABSTRACT FROM AUTHOR]

Aiming at improving the classification accuracy with limited numbers of labeled pixels in polarimetric synthetic aperture radar (PolSAR) image classification task, this paper presents a graph-based semisupervised deep learning model for PolSAR image classification. It models the PolSAR image as an undirected graph, where the nodes correspond to the labeled and unlabeled pixels, and the weighted edges represent similarities between the pixels. Upon the graph, we design an energy function incorporating a semisupervision term, a convolutional neural network (CNN) term, and a pairwise smoothness term. The employed CNN extracts abstract and data-driven polarimetric features and outputs class label predictions to the graph model. The semisupervision term enforces the category label constraints on the human-labeled pixels. The pairwise smoothness term encourages class label smoothness and the alignment of class label boundaries with the image edges. Starting from an initialized class label map generated based on $K$ -Wishart distribution hypothesis or superpixel segmentation of PauliRGB images, we iteratively and alternately optimize the defined energy function until it converges. We conducted experiments on two real benchmark PolSAR images, and extensive experiments demonstrated that our approach achieved the state-of-the-art results for PolSAR image classification. [ABSTRACT FROM AUTHOR]

Accurate segmentation of pelvic organs (i.e., prostate, bladder, and rectum) from CT image is crucial for effective prostate cancer radiotherapy. However, it is a challenging task due to: 1) low soft tissue contrast in CT images and 2) large shape and appearance variations of pelvic organs. In this paper, we employ a two-stage deep learning-based method, with a novel distinctive curve-guided fully convolutional network (FCN), to solve the aforementioned challenges. Specifically, the first stage is for fast and robust organ detection in the raw CT images. It is designed as a coarse segmentation network to provide region proposals for three pelvic organs. The second stage is for fine segmentation of each organ, based on the region proposal results. To better identify those indistinguishable pelvic organ boundaries, a novel morphological representation, namely, distinctive curve, is also introduced to help better conduct the precise segmentation. To implement this, in this second stage, a multi-task FCN is initially utilized to learn the distinctive curve and the segmentation map separately and then combine these two tasks to produce accurate segmentation map. The final segmentation results of all three pelvic organs are generated by a weighted max-voting strategy. We have conducted exhaustive experiments on a large and diverse pelvic CT data set for evaluating our proposed method. The experimental results demonstrate that our proposed method is accurate and robust for this challenging segmentation task, by also outperforming the state-of-the-art segmentation methods. [ABSTRACT FROM AUTHOR]

Conversations in the intelligent vehicles are usually short utterance. As the durations of the short utterances are small (e.g., less than 3 s), it is difficult to learn sufficient information to distinguish the type of languages. In this paper, we propose an end-to-end short utterances based speech language identification (SLI) approach, which is especially suitable for the short utterance based language identification. This approach is implemented with a long short-term memory (LSTM) neural network, which is designed for the SLI application in intelligent vehicles. The features used for LSTM learning are generated by a transfer learning method. The bottleneck features of a deep neural network, which are obtained for a mandarin acoustic-phonetic classifier, are used for the LSTM training. In order to improve the SLD accuracy with short utterances, a phase vocoder based time-scale modification method is utilized to reduce/increase the speech rate of the test utterance. By connecting the normal, speech rate reduced, and speech rate increased utterances, we can extend the length of the test utterances such that the performance of the SLI system is improved. The experimental results on the AP17-OLR database demonstrate that the proposed method can improve the performance of SLD, especially on short utterance. The proposed SLI has robust performance under the vehicular noisy environment. [ABSTRACT FROM AUTHOR]

Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structure, there also exists rich information about social actors, such as user profiles of friendship networks and textual content of citation networks. These rich attribute information of social actors reveal the homophily effect, exerting huge impacts on the formation of social networks. In this paper, we explore the rich evidence source of attributes in social networks to improve network embedding. We propose a generic Attributed Social Network Embedding framework (ASNE), which learns representations for social actors (i.e., nodes) by preserving both thestructural proximityandattribute proximity. While thestructural proximitycaptures the global network structure, theattribute proximityaccounts for the homophily effect. To justify our proposal, we conduct extensive experiments on four real-world social networks. Compared to the state-of-the-art network embedding approaches,ASNEcan learn more informative representations, achieving substantial gains on the tasks of link prediction and node classification. Specifically,ASNEsignificantly outperformsnode2vecwith an 8.2 percent relative improvement on the link prediction task, and a 12.7 percent gain on the node classification task. [ABSTRACT FROM AUTHOR]

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple yet effective approach for segmenting object proposals via a deep architecture of recursive neural networks (ReNNs), which hierarchically groups regions for detecting object candidates over scales. Unlike traditional methods that mainly adopt fixed similarity measures for merging regions or finding object proposals, our approach adaptively learns the region merging similarity and the objectness measure during the process of hierarchical region grouping. Specifically, guided by a structured loss, the ReNN model jointly optimizes the cross-region similarity metric with the region merging process as well as the objectness prediction. During inference of the object proposal generation, we introduce randomness into the greedy search to cope with the ambiguity of grouping regions. Extensive experiments on standard benchmarks, e.g., PASCAL VOC and ImageNet, suggest that our approach is capable of producing object proposals with high recall while well preserving the object boundaries and outperforms other existing methods in both accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Depth estimation from single monocular images is a key component in scene understanding. Most existing algorithms formulate depth estimation as a regression problem due to the continuous property of depths. However, the depth value of input data can hardly be regressed exactly to the ground-truth value. In this paper, we propose to formulate depth estimation as a pixelwise classification task. Specifically, we first discretize the continuous ground-truth depths into several bins and label the bins according to their depth ranges. Then, we solve the depth estimation problem as classification by training a fully convolutional deep residual network. Compared with estimating the exact depth of a single point, it is easier to estimate its depth range. More importantly, by performing depth classification instead of regression, we can easily obtain the confidence of a depth prediction in the form of probability distribution. With this confidence, we can apply an information gain loss to make use of the predictions that are close to ground-truth during training, as well as fully-connected conditional random fields for post-processing to further improve the performance. We test our proposed method on both indoor and outdoor benchmark RGB-Depth datasets and achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of the CNN help people clarify the logic encoded in the CNN, i.e., answering what patterns the CNN extracts from an input image and uses for prediction. We have tested our method using different benchmark CNNs with various architectures to demonstrate the broad applicability of our method. Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters. [ABSTRACT FROM AUTHOR]

The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks, such as GoogleNet and VGG, novel object detection frameworks, such as R-CNN and its successors, Fast R-CNN, and Faster R-CNN, play an essential role in improving the state of the art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this paper, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e., tubelets with convolutional neueral networks. The proposed framework won newly introduced an object-detection-from-video task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015. Code is publicly available at https://github.com/myfavouritekk/T-CNN. [ABSTRACT FROM AUTHOR]

Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision especially in high-level vision applications, such as recognition and understanding. However, it is rarely used to solve low-level vision problems such as image compression studied in this paper. Here, we move forward a step and propose a novel compression framework based on CNNs. To achieve high-quality image compression at low bit rates, two CNNs are seamlessly integrated into an end-to-end compression framework. The first CNN, named compact convolutional neural network (ComCNN), learns an optimal compact representation from an input image, which preserves the structural information and is then encoded using an image codec (e.g., JPEG, JPEG2000, or BPG). The second CNN, named reconstruction convolutional neural network (RecCNN), is used to reconstruct the decoded image with high quality in the decoding end. To make two CNNs effectively collaborate, we develop a unified end-to-end learning algorithm to simultaneously learn ComCNN and RecCNN, which facilitates the accurate reconstruction of the decoded image using RecCNN. Such a design also makes the proposed compression framework compatible with existing image coding standards. Experimental results validate that the proposed compression framework greatly outperforms several compression frameworks that use existing image coding standards with the state-of-the-art deblocking or denoising post-processing methods. [ABSTRACT FROM AUTHOR]