Search

Quantum random access memory (QRAM) promises simultaneous data queries at multiple memory locations, with data retrieved in coherent superpositions, essential for achieving quantum speedup in many quantum algorithms. We introduce a transmon-controlled phonon router and propose a QRAM implementation by connecting these routers in a tree-like architecture. The router controls the motion of itinerant surface acoustic wave phonons based on the state of the control transmon, implementing the core functionality of conditional routing for QRAM. Our QRAM design is compact, supports fast routing operations, and avoids frequency crowding. Additionally, we propose a hybrid dual-rail encoding method to detect dominant loss errors without additional hardware, a versatile approach applicable to other QRAM platforms. Our estimates indicate that the proposed QRAM platform can achieve high heralding rates using current device parameters, with heralding fidelity primarily limited by transmon dephasing.

Vision-language navigation (VLN) is a critical domain within embedded intelligence, requiring agents to navigate 3D environments based on natural language instructions. Traditional VLN research has focused on improving environmental understanding and decision accuracy. However, these approaches often exhibit a significant performance gap when agents are deployed in novel environments, mainly due to the limited diversity of training data. Expanding datasets to cover a broader range of environments is impractical and costly. We propose the Vision-Language Navigation with Continual Learning (VLNCL) paradigm to address this challenge. In this paradigm, agents incrementally learn new environments while retaining previously acquired knowledge. VLNCL enables agents to maintain an environmental memory and extract relevant knowledge, allowing rapid adaptation to new environments while preserving existing information. We introduce a novel dual-loop scenario replay method (Dual-SR) inspired by brain memory replay mechanisms integrated with VLN agents. This method facilitates consolidating past experiences and enhances generalization across new tasks. By utilizing a multi-scenario memory buffer, the agent efficiently organizes and replays task memories, thereby bolstering its ability to adapt quickly to new environments and mitigating catastrophic forgetting. Our work pioneers continual learning in VLN agents, introducing a novel experimental setup and evaluation metrics. We demonstrate the effectiveness of our approach through extensive evaluations and establish a benchmark for the VLNCL paradigm. Comparative experiments with existing continual learning and VLN methods show significant improvements, achieving state-of-the-art performance in continual learning ability and highlighting the potential of our approach in enabling rapid adaptation while preserving prior knowledge.

Vision Language Navigation in Continuous Environments (VLN-CE) represents a frontier in embodied AI, demanding agents to navigate freely in unbounded 3D spaces solely guided by natural language instructions. This task introduces distinct challenges in multimodal comprehension, spatial reasoning, and decision-making. To address these challenges, we introduce Cog-GA, a generative agent founded on large language models (LLMs) tailored for VLN-CE tasks. Cog-GA employs a dual-pronged strategy to emulate human-like cognitive processes. Firstly, it constructs a cognitive map, integrating temporal, spatial, and semantic elements, thereby facilitating the development of spatial memory within LLMs. Secondly, Cog-GA employs a predictive mechanism for waypoints, strategically optimizing the exploration trajectory to maximize navigational efficiency. Each waypoint is accompanied by a dual-channel scene description, categorizing environmental cues into 'what' and 'where' streams as the brain. This segregation enhances the agent's attentional focus, enabling it to discern pertinent spatial information for navigation. A reflective mechanism complements these strategies by capturing feedback from prior navigation experiences, facilitating continual learning and adaptive replanning. Extensive evaluations conducted on VLN-CE benchmarks validate Cog-GA's state-of-the-art performance and ability to simulate human-like navigation behaviors. This research significantly contributes to the development of strategic and interpretable VLN-CE agents.

Superconducting qubits provide a promising approach to large-scale fault-tolerant quantum computing. However, qubit connectivity on a planar surface is typically restricted to only a few neighboring qubits. Achieving longer-range and more flexible connectivity, which is particularly appealing in light of recent developments in error-correcting codes, however usually involves complex multi-layer packaging and external cabling, which is resource-intensive and can impose fidelity limitations. Here, we propose and realize a high-speed on-chip quantum processor that supports reconfigurable all-to-all coupling with a large on-off ratio. We implement the design in a four-node quantum processor, built with a modular design comprising a wiring substrate coupled to two separate qubit-bearing substrates, each including two single-qubit nodes. We use this device to demonstrate reconfigurable controlled-Z gates across all qubit pairs, with a benchmarked average fidelity of $96.00\%\pm0.08\%$ and best fidelity of $97.14\%\pm0.07\%$, limited mainly by dephasing in the qubits. We also generate multi-qubit entanglement, distributed across the separate modules, demonstrating GHZ-3 and GHZ-4 states with fidelities of $88.15\%\pm0.24\%$ and $75.18\%\pm0.11\%$, respectively. This approach promises efficient scaling to larger-scale quantum circuits, and offers a pathway for implementing quantum algorithms and error correction schemes that benefit from enhanced qubit connectivity.

Quantum communication testbeds provide a useful resource for experimentally investigating a variety of communication protocols. Here we demonstrate a superconducting circuit testbed with bidirectional multi-photon state transfer capability using time-domain shaped wavepackets. The system we use to achieve this comprises two remote nodes, each including a tunable superconducting transmon qubit and a tunable microwave-frequency resonator, linked by a 2 m-long superconducting coplanar waveguide, which serves as a transmission line. We transfer both individual and superposition Fock states between the two remote nodes, and additionally show that this bidirectional state transfer can be done simultaneously, as well as used to entangle elements in the two nodes., Comment: Main Paper has 6 pages, 4 figures. Supplementary has 14 pages, 16 figures, 2 tables

In the field of quantum computation and communication there is a compelling need for quantum-coherent frequency conversion between microwave electronics and infra-red optics. A promising platform for this is an optomechanical crystal resonator that uses simultaneous photonic and phononic crystals to create a co-localized cavity coupling an electromagnetic mode to an acoustic mode, which then via electromechanical interactions can undergo direct transduction to electronics. The majority of work in this area has been on one-dimensional nanobeam resonators which provide strong optomechanical couplings but, due to their geometry, suffer from an inability to dissipate heat produced by the laser pumping required for operation. Recently, a quasi-two-dimensional optomechanical crystal cavity was developed in silicon exhibiting similarly strong coupling with better thermalization, but at a mechanical frequency above optimal qubit operating frequencies. Here we adapt this design to gallium arsenide, a natural thin-film single-crystal piezoelectric that can incorporate electromechanical interactions, obtaining a mechanical resonant mode at f_m ~ 4.5 GHz ideal for superconducting qubits, and demonstrating optomechanical coupling g_om/(2pi) ~ 650 kHz.

Spiking Neural Networks (SNNs) have garnered widespread interest for their energy efficiency and brain-inspired event-driven properties. While recent methods like Spiking-YOLO have expanded the SNNs to more challenging object detection tasks, they often suffer from high latency and low detection accuracy, making them difficult to deploy on latency sensitive mobile platforms. Furthermore, the conversion method from Artificial Neural Networks (ANNs) to SNNs is hard to maintain the complete structure of the ANNs, resulting in poor feature representation and high conversion errors. To address these challenges, we propose two methods: timesteps compression and spike-time-dependent integrated (STDI) coding. The former reduces the timesteps required in ANN-SNN conversion by compressing information, while the latter sets a time-varying threshold to expand the information holding capacity. We also present a SNN-based ultra-low latency and high accurate object detection model (SUHD) that achieves state-of-the-art performance on nontrivial datasets like PASCAL VOC and MS COCO, with about remarkable 750x fewer timesteps and 30% mean average precision (mAP) improvement, compared to the Spiking-YOLO on MS COCO datasets. To the best of our knowledge, SUHD is the deepest spike-based object detection model to date that achieves ultra low timesteps to complete the lossless conversion., Comment: 14 pages, 10 figures

In circuit quantum electrodynamics (QED), qubits are typically measured using dispersively-coupled readout resonators. Coupling between each readout resonator and its electrical environment however reduces the qubit lifetime via the Purcell effect. Inserting a Purcell filter counters this effect while maintaining high readout fidelity, but reduces measurement bandwidth and thus limits multiplexing readout capacity. In this letter, we develop and implement a multi-stage bandpass Purcell filter that yields better qubit protection while simultaneously increasing measurement bandwidth and multiplexed capacity. We report on the experimental performance of our transmission-line--based implementation of this approach, a flexible design that can easily be integrated with current scaled-up, long coherence time superconducting quantum processors.

Linear optical quantum computing provides a desirable approach to quantum computing, with a short list of required elements. The similarity between photons and phonons points to the interesting potential for linear mechanical quantum computing (LMQC), using phonons in place of photons. While single-phonon sources and detectors have been demonstrated, a phononic beamsplitter element remains an outstanding requirement. Here we demonstrate such an element, using two superconducting qubits to fully characterize a beamsplitter with single phonons. We further use the beamsplitter to demonstrate two-phonon interference, a requirement for two-qubit gates, completing the toolbox needed for LMQC. This advance brings linear quantum computing to a fully solid-state system, along with straightforward conversion between itinerant phonons and superconducting qubits.

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have only encountered some partial classes and images. Unlike other works on the NCD, we leverage the prototypes to emphasize the importance of category discrimination and alleviate the issue of missing annotations of novel classes. Concretely, we propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. In the first stage, we obtain a robust feature extractor, which could serve for all images with base and novel categories. This ability of instance and category discrimination of the feature extractor is boosted by self-supervised learning and adaptive prototypes. In the second stage, we utilize the prototypes again to rectify offline pseudo labels and train a final parametric classifier for category clustering. We conduct extensive experiments on four benchmark datasets and demonstrate the effectiveness and robustness of the proposed method with state-of-the-art performance., Comment: In Submission

Parametrically driving an optical cavity that simultaneously couples to an atomic ensemble quantum memory enables in-situ generation of multimode photon-memory entanglement. A high-rate bi-party photon-memory entanglement can be generated even after discarding one entangled optical mode. This protocol can be realized with existing technologies based on photonic resonators integrated with a rare-earth-ion doped quantum memory. The proposed scheme shows significant advantages in entanglement generation rates compared with prevailing quantum memory protocols and experiments, with theoretical Ebit rates of tens of MHz without fine-tuned operating conditions. Such a photon-memory entanglement source offers a versatile resource for quantum networking and interconnect applications., Comment: 5 pages, 4 figures

Object goal visual navigation is a challenging task that aims to guide a robot to find the target object based on its visual observation, and the target is limited to the classes pre-defined in the training stage. However, in real households, there may exist numerous target classes that the robot needs to deal with, and it is hard for all of these classes to be contained in the training stage. To address this challenge, we study the zero-shot object goal visual navigation task, which aims at guiding robots to find targets belonging to novel classes without any training samples. To this end, we also propose a novel zero-shot object navigation framework called semantic similarity network (SSNet). Our framework use the detection results and the cosine similarity between semantic word embeddings as input. Such type of input data has a weak correlation with classes and thus our framework has the ability to generalize the policy to novel classes. Extensive experiments on the AI2-THOR platform show that our model outperforms the baseline models in the zero-shot object navigation task, which proves the generalization ability of our model. Our code is available at: https://github.com/pioneer-innovation/Zero-Shot-Object-Navigation.

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem. First, a region feature (RF) alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal RFs. Second, we propose a novel region of interest (RoI) jitter strategy to improve the robustness to unexpected shift patterns. Third, we present a new multimodal feature fusion method that selects the more reliable feature and suppresses the less useful one via feature reweighting. In addition, by locating bounding boxes in both modalities and building their relationships, we provide novel multimodal labeling named KAIST-Paired. Extensive experiments on 2-D and 3-D object detection, RGB-T, and RGB-D datasets demonstrate the effectiveness and robustness of our method., Comment: Journal extension of the previous conference paper arXiv:1901.02645, see IEEE page https://ieeexplore.ieee.org/document/9523596

Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, the domain shift caused by the sim2real gap is inevitable, posing a crucial challenge to the segmentation model. In this paper, we emphasize the adaptation process across sim2real domains and model it as a learning problem on the BatchNorm parameters of a simulation-trained model. Specifically, we propose a novel non-parametric entropy objective, which formulates the learning objective for the test-time adaptation in an open-world manner. Then, a cross-modality knowledge distillation objective is further designed to encourage the test-time knowledge transfer for feature enhancement. Our approach can be efficiently implemented with only test images, without requiring annotations or revisiting the large-scale synthetic training data. Besides significant time savings, the proposed method consistently improves segmentation results on the overlap and boundary metrics, achieving state-of-the-art performance on unseen object instance segmentation., Comment: Accepted to ICRA 2023

Rapid, accurate and robust detection of looming objects in cluttered moving backgrounds is a significant and challenging problem for robotic visual systems to perform collision detection and avoidance tasks. Inspired by the neural circuit of elementary motion vision in the mammalian retina, this paper proposes a bioinspired approach-sensitive neural network (ASNN) that contains three main contributions. Firstly, a direction-selective visual processing module is built based on the spatiotemporal energy framework, which can estimate motion direction accurately via only two mutually perpendicular spatiotemporal filtering channels. Secondly, a novel approach-sensitive neural network is modeled as a push-pull structure formed by ON and OFF pathways, which responds strongly to approaching motion while insensitivity to lateral motion. Finally, a method of directionally selective inhibition is introduced, which is able to suppress the translational backgrounds effectively. Extensive synthetic and real robotic experiments show that the proposed model is able to not only detect collision accurately and robustly in cluttered and dynamic backgrounds but also extract more collision information like position and direction, for guiding rapid decision making.

Robust and accurate detection of small moving targets in cluttered moving backgrounds is a significant and challenging problem for robotic visual systems to perform search and tracking tasks. Inspired by the neural circuitry of elementary motion vision in the mammalian retina, this paper proposes a bioinspired retinal neural network based on a new neurodynamics-based temporal filtering and multiform 2-D spatial Gabor filtering. This model can estimate motion direction accurately via only two perpendicular spatiotemporal filtering signals, and respond to small targets of different sizes and velocities by adjusting the dendrite field size of the spatial filter. Meanwhile, an algorithm of directionally selective inhibition is proposed to suppress the target-like features in the moving background, which can reduce the influence of background motion effectively. Extensive synthetic and real-data experiments show that the proposed model works stably for small targets of a wider size and velocity range, and has better detection performance than other bioinspired models. Additionally, it can also extract the information of motion direction and motion energy accurately and rapidly.

Due to the non-smoothness of the Hinge loss in SVM, it is difficult to obtain a faster convergence rate with modern optimization algorithms. In this paper, we introduce two smooth Hinge losses $\psi_G(\alpha;\sigma)$ and $\psi_M(\alpha;\sigma)$ which are infinitely differentiable and converge to the Hinge loss uniformly in $\alpha$ as $\sigma$ tends to $0$. By replacing the Hinge loss with these two smooth Hinge losses, we obtain two smooth support vector machines(SSVMs), respectively. Solving the SSVMs with the Trust Region Newton method (TRON) leads to two quadratically convergent algorithms. Experiments in text classification tasks show that the proposed SSVMs are effective in real-world applications. We also introduce a general smooth convex loss function to unify several commonly-used convex loss functions in machine learning. The general framework provides smooth approximation functions to non-smooth convex loss functions, which can be used to obtain smooth models that can be solved with faster convergent optimization algorithms.

Imbalanced classification tasks are widespread in many real-world applications. For such classification tasks, in comparison with the accuracy rate, it is usually much more appropriate to use non-decomposable performance measures such as the Area Under the receiver operating characteristic Curve (AUC) and the $F_\beta$ measure as the classification criterion since the label class is imbalanced. On the other hand, the minimax probability machine is a popular method for binary classification problems and aims at learning a linear classifier by maximizing the accuracy rate, which makes it unsuitable to deal with imbalanced classification tasks. The purpose of this paper is to develop a new minimax probability machine for the $F_\beta$ measure, called MPMF, which can be used to deal with imbalanced classification tasks. A brief discussion is also given on how to extend the MPMF model for several other non-decomposable performance measures listed in the paper. To solve the MPMF model effectively, we derive its equivalent form which can then be solved by an alternating descent method to learn a linear classifier. Further, the kernel trick is employed to derive a nonlinear MPMF model to learn a nonlinear classifier. Several experiments on real-world benchmark datasets demonstrate the effectiveness of our new model.

Remote tiny face detection applied in unmanned system is a challeng-ing work. The detector cannot obtain sufficient context semantic information due to the relatively long distance. The received poor fine-grained features make the face detection less accurate and robust. To solve the problem of long-distance detection of tiny faces, we propose an enhanced network model (YOLOv3-C) based on the YOLOv3 algorithm for unmanned platform. In this model, we bring in multi-scale features from feature pyramid networks and make the features fu-sion to adjust prediction feature map of the output, which improves the sensitivity of the entire algorithm for tiny target faces. The enhanced model improves the accuracy of tiny face detection in the cases of long-distance and high-density crowds. The experimental evaluation results demonstrated the superior perfor-mance of the proposed YOLOv3-C in comparison with other relevant detectors in remote tiny face detection. It is worth mentioning that our proposed method achieves comparable performance with the state of the art YOLOv4[1] in the tiny face detection tasks.

Action recognition is an important and challenging problem in video analysis. Although the past decade has witnessed progress in action recognition with the development of deep learning, such process has been slow in competitive sports content analysis. To promote the research on action recognition from competitive sports video clips, we introduce a Figure Skating Dataset (FSD-10) for finegrained sports content analysis. To this end, we collect 1484 clips from the worldwide figure skating championships in 2017-2018, which consist of 10 different actions in men/ladies programs. Each clip is at a rate of 30 frames per second with resolution 1080 $\times$ 720. These clips are then annotated by experts in type, grade of execution, skater info, .etc. To build a baseline for action recognition in figure skating, we evaluate state-of-the-art action recognition methods on FSD-10. Motivated by the idea that domain knowledge is of great concern in sports field, we propose a keyframe based temporal segment network (KTSN) for classification and achieve remarkable performance. Experimental results demonstrate that FSD-10 is an ideal dataset for benchmarking action recognition algorithms, as it requires to accurately extract action motions rather than action poses. We hope FSD-10, which is designed to have a large collection of finegrained actions, can serve as a new challenge to develop more robust and advanced action recognition models.

Manifold learning now plays a very important role in machine learning and many relevant applications. Although its superior performance in dealing with nonlinear data distribution, data sparsity is always a thorny knot. There are few researches to well handle it in manifold learning. In this paper, we propose Hierarchic Neighbors Embedding (HNE), which enhance local connection by the hierarchic combination of neighbors. After further analyzing topological connection and reconstruction performance, three different versions of HNE are given. The experimental results show that our methods work well on both synthetic data and high-dimensional real-world tasks. HNE develops the outstanding advantages in dealing with general data. Furthermore, comparing with other popular manifold learning methods, the performance on sparse samples and weak-connected manifolds is better for HNE.

In this paper, we present an overview of robotic peg-in-hole assembly and analyze two main strategies: contact model-based and contact model-free strategies. More specifically, we first introduce the contact model control approaches, including contact state recognition and compliant control two steps. Additionally, we focus on a comprehensive analysis of the whole robotic assembly system. Second, without the contact state recognition process, we decompose the contact model-free learning algorithms into two main subfields: learning from demonstrations and learning from environments (mainly based on reinforcement learning). For each subfield, we survey the landmark studies and ongoing research to compare the different categories. We hope to strengthen the relation between these two research communities by revealing the underlying links. Ultimately, the remaining challenges and open questions in the field of robotic peg-in-hole assembly community is discussed. The promising directions and potential future work are also considered.

Human emotion recognition is an important direction in the field of biometric and information forensics. However, most existing human emotion research are based on the single RGB view. In this paper, we introduce a RGBD video-emotion dataset and a RGBD face-emotion dataset for research. To our best knowledge, this may be the first RGBD video-emotion dataset. We propose a new supervised nonlinear multi-view laplacian eigenmaps (MvLE) approach and a multihidden-layer out-of-sample network (MHON) for RGB-D humanemotion recognition. To get better representations of RGB view and depth view, MvLE is used to map the training set of both views from original space into the common subspace. As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views. Finally, MHON is used to get the low-dimensional representations of test data and predict their labels. MvLE can deal with the cases that RGB view and depth view have different size of features, even different number of samples and classes. And our methods can be easily extended to more than two views. The experiment results indicate the effectiveness of our methods over some state-of-art methods.

Supervised learning methods are widely used in machine learning. However, the lack of labels in existing data limits the application of these technologies. Visual interactive learning (VIL) compared with computers can avoid semantic gap, and solve the labeling problem of small label quantity (SLQ) samples in a groundbreaking way. In order to fully understand the importance of VIL to the interaction process, we re-summarize the interactive learning related algorithms (e.g. clustering, classification, retrieval etc.) from the perspective of VIL. Note that, perception and cognition are two main visual processes of VIL. On this basis, we propose a perceptual visual interactive learning (PVIL) framework, which adopts gestalt principle to design interaction strategy and multi-dimensionality reduction (MDR) to optimize the process of visualization. The advantage of PVIL framework is that it combines computer's sensitivity of detailed features and human's overall understanding of global tasks. Experimental results validate that the framework is superior to traditional computer labeling methods (such as label propagation) in both accuracy and efficiency, which achieves significant classification results on dense distribution and sparse classes dataset.

We investigate the diagonal entropy for ground states of the extended Kitaev chains with extensive pairing and hopping terms. The systems contain rich topological phases equivalently represented by topological invariant winding numbers and Majorana zero modes. Both the finite size scaling law and block scaling law of the diagonal entropy are studied, which indicates that the diagonal entropy demonstrates volume effect. The parameter of volume term is regarded as the diagonal entropy density, which can identify the critical points of symmetry-protected topological phase transitions efficiently in the studied models, even for those with higher winding numbers. The formulation of block scaling law and the capability of diagonal entropy density in detecting topological phase transitions are independent of the chosen bases. In order to manifest the advantage of diagonal entropy, we also calculate the global entanglement, which can not show clear signatures of the topological phase transitions. This work provides a new quantum-informatic approach to characterize the feature of the topologically ordered states and may motivate a deep understanding of the quantum coherence and diagonal entropy in various condensed matter systems.

Traditional image clustering methods take a two-step approach, feature learning and clustering, sequentially. However, recent research results demonstrated that combining the separated phases in a unified framework and training them jointly can achieve a better performance. In this paper, we first introduce fully convolutional auto-encoders for image feature learning and then propose a unified clustering framework to learn image representations and cluster centers jointly based on a fully convolutional auto-encoder and soft $k$-means scores. At initial stages of the learning procedure, the representations extracted from the auto-encoder may not be very discriminative for latter clustering. We address this issue by adopting a boosted discriminative distribution, where high score assignments are highlighted and low score ones are de-emphasized. With the gradually boosted discrimination, clustering assignment scores are discriminated and cluster purities are enlarged. Experiments on several vision benchmark datasets show that our methods can achieve a state-of-the-art performance., Comment: 27 pages

Visual saliency detection aims at identifying the most visually distinctive parts in an image, and serves as a pre-processing step for a variety of computer vision and image processing tasks. To this end, the saliency detection procedure must be as fast and compact as possible and optimally processes input images in a real time manner. It is an essential application requirement for the saliency detection task. However, contemporary detection methods often utilize some complicated procedures to pursue feeble improvements on the detection precession, which always take hundreds of milliseconds and make them not easy to be applied practically. In this paper, we tackle this problem by proposing a fast and compact saliency score regression network which employs fully convolutional network, a special deep convolutional neural network, to estimate the saliency of objects in images. It is an extremely simplified end-to-end deep neural network without any pre-processings and post-processings. When given an image, the network can directly predict a dense full-resolution saliency map (image-to-image prediction). It works like a compact pipeline which effectively simplifies the detection procedure. Our method is evaluated on six public datasets, and experimental results show that it can achieve comparable or better precision performance than the state-of-the-art methods while get a significant improvement in detection speed (35 FPS, processing in real time).

The $k$-means clustering algorithm is popular but has the following main drawbacks: 1) the number of clusters, $k$, needs to be provided by the user in advance, 2) it can easily reach local minima with randomly selected initial centers, 3) it is sensitive to outliers, and 4) it can only deal with well separated hyperspherical clusters. In this paper, we propose a Local Density Peaks Searching (LDPS) initialization framework to address these issues. The LDPS framework includes two basic components: one of them is the local density that characterizes the density distribution of a data set, and the other is the local distinctiveness index (LDI) which we introduce to characterize how distinctive a data point is compared with its neighbors. Based on these two components, we search for the local density peaks which are characterized with high local densities and high LDIs to deal with 1) and 2). Moreover, we detect outliers characterized with low local densities but high LDIs, and exclude them out before clustering begins. Finally, we apply the LDPS initialization framework to $k$-medoids, which is a variant of $k$-means and chooses data samples as centers, with diverse similarity measures other than the Euclidean distance to fix the last drawback of $k$-means. Combining the LDPS initialization framework with $k$-means and $k$-medoids, we obtain two novel clustering methods called LDPS-means and LDPS-medoids, respectively. Experiments on synthetic data sets verify the effectiveness of the proposed methods, especially when the ground truth of the cluster number $k$ is large. Further, experiments on several real world data sets, Handwritten Pendigits, Coil-20, Coil-100 and Olivetti Face Database, illustrate that our methods give a superior performance than the analogous approaches on both estimating $k$ and unsupervised object categorization., Comment: 16 pages, 9 figures, journal paper

Incompatibility of image descriptor and ranking is always neglected in image retrieval. In this paper, manifold learning and Gestalt psychology theory are involved to solve the incompatibility problem. A new holistic descriptor called Perceptual Uniform Descriptor (PUD) based on Gestalt psychology is proposed, which combines color and gradient direction to imitate the human visual uniformity. PUD features in the same class images distributes on one manifold in most cases because PUD improves the visual uniformity of the traditional descriptors. Thus, we use manifold ranking and PUD to realize image retrieval. Experiments were carried out on five benchmark data sets, and the proposed method can greatly improve the accuracy of image retrieval. Our experimental results in the Ukbench and Corel-1K datasets demonstrated that N-S score reached to 3.58 (HSV 3.4) and mAP to 81.77% (ODBTC 77.9%) respectively by utilizing PUD which has only 280 dimension. The results are higher than other holistic image descriptors (even some local ones) and state-of-the-arts retrieval methods.

Poisson denoising is an essential issue for various imaging applications, such as night vision, medical imaging and microscopy. State-of-the-art approaches are clearly dominated by patch-based non-local methods in recent years. In this paper, we aim to propose a local Poisson denoising model with both structure simplicity and good performance. To this end, we consider a variational modeling to integrate the so-called Fields of Experts (FoE) image prior, that has proven an effective higher-order Markov Random Fields (MRF) model for many classic image restoration problems. We exploit several feasible variational variants for this task. We start with a direct modeling in the original image domain by taking into account the Poisson noise statistics, which performs generally well for the cases of high SNR. However, this strategy encounters problem in cases of low SNR. Then we turn to an alternative modeling strategy by using the Anscombe transform and Gaussian statistics derived data term. We retrain the FoE prior model directly in the transform domain. With the newly trained FoE model, we end up with a local variational model providing strongly competitive results against state-of-the-art non-local approaches, meanwhile bearing the property of simple structure. Furthermore, our proposed model comes along with an additional advantage, that the inference is very efficient as it is well-suited for parallel computation on GPUs. For images of size $512 \times 512$, our GPU implementation takes less than 1 second to produce state-of-the-art Poisson denoising performance., Comment: 31 pages, 10 figures. To appear in SIAM Journal on Imaging Sciences

Manifold distances are very effective tools for visual object recognition. However, most of the traditional manifold distances between images are based on the pixel-level comparison and thus easily affected by image rotations and translations. In this paper, we propose a new manifold distance to model the dissimilarities between visual objects based on the Complex Wavelet Structural Similarity (CW-SSIM) index. The proposed distance is more robust to rotations and translations of images than the traditional manifold distance and the CW-SSIM index based distance. In addition, the proposed distance is combined with the $k$-medoids clustering method to derive a new clustering method for visual object categorization. Experiments on Coil-20, Coil-100 and Olivetti Face Databases show that the proposed distance measure is better for visual object categorization than both the traditional manifold distances and the CW-SSIM index based distances.

Integration between biology and information science benefits both fields. Many related models have been proposed, such as computational visual cognition models, computational motor control models, integrations of both and so on. In general, the robustness and precision of recognition is one of the key problems for object recognition models. In this paper, inspired by features of human recognition process and their biological mechanisms, a new integrated and dynamic framework is proposed to mimic the semantic extraction, concept formation and feature re-selection in human visual processing. The main contributions of the proposed model are as follows: (1) Semantic feature extraction: Local semantic features are learnt from episodic features that are extracted from raw images through a deep neural network; (2) Integrated concept formation: Concepts are formed with local semantic information and structural information learnt through network. (3) Feature re-selection: When ambiguity is detected during recognition process, distinctive features according to the difference between ambiguous candidates are re-selected for recognition. Experimental results on hand-written digits and facial shape dataset show that, compared with other methods, the new proposed model exhibits higher robustness and precision for visual recognition, especially in the condition when input samples are smantic ambiguous. Meanwhile, the introduced biological mechanisms further strengthen the interaction between neuroscience and information science.

In recent years, the interdisciplinary research between information science and neuroscience has been a hotspot. In this paper, based on recent biological findings, we proposed a new model to mimic visual information processing, motor planning and control in central and peripheral nervous systems of human. Main steps of the model are as follows: 1) Simulating "where" pathway in human: the Selective Search method is applied to simulate the function of human dorsal visual pathway to localize object candidates; 2) Simulating "what" pathway in human: a Convolutional Deep Belief Network is applied to simulate the hierarchical structure and function of human ventral visual pathway for object recognition; 3) Simulating motor planning process in human: habitual motion planning process in human is simulated, and motor commands are generated from the combination of control signals from past experiences; 4) Simulating precise movement control in human: calibrated control signals, which mimic the adjustment for movement from cerebellum in human, are generated and updated from calibration of movement errors in past experiences, and sent to the movement model to achieve high precision. The proposed framework mimics structures and functions of human recognition, visuomotor coordination and precise motor control. Experiments on object localization, recognition and movement control demonstrate that the new proposed model can not only accomplish visuomotor coordination tasks, but also achieve high precision movement with learning ability. Meanwhile, the results also prove the validity of the introduced mechanisms. Furthermore, the proposed model could be generalized and applied to other systems, such as mechanical and electrical systems in robotics, to achieve fast response, high precision movement with learning ability., Comment: 12 pages, 13 figures

We propose a weighted common subgraph (WCS) matching algorithm to find the most similar subgraphs in two labeled weighted graphs. WCS matching, as a natural generalization of the equal-sized graph matching or subgraph matching, finds wide applications in many computer vision and machine learning tasks. In this paper, the WCS matching is first formulated as a combinatorial optimization problem over the set of partial permutation matrices. Then it is approximately solved by a recently proposed combinatorial optimization framework - Graduated NonConvexity and Concavity Procedure (GNCCP). Experimental comparisons on both synthetic graphs and real world images validate its robustness against noise level, problem size, outlier number, and edge density., Comment: 6 pages, 5 figures, the second round revision in IEEE TNNLS

The Fields of Experts (FoE) image prior model, a filter-based higher-order Markov Random Fields (MRF) model, has been shown to be effective for many image restoration problems. Motivated by the successes of FoE-based approaches, in this letter, we propose a novel variational model for multiplicative noise reduction based on the FoE image prior model. The resulted model corresponds to a non-convex minimization problem, which can be solved by a recently published non-convex optimization algorithm. Experimental results based on synthetic speckle noise and real synthetic aperture radar (SAR) images suggest that the performance of our proposed method is on par with the best published despeckling algorithm. Besides, our proposed model comes along with an additional advantage, that the inference is extremely efficient. {Our GPU based implementation takes less than 1s to produce state-of-the-art despeckling performance.}, Comment: 5 pages, 5 figures, to appear in IEEE Signal Processing Letters

In this paper we propose the Graduated NonConvexity and Graduated Concavity Procedure (GNCGCP) as a general optimization framework to approximately solve the combinatorial optimization problems on the set of partial permutation matrices. GNCGCP comprises two sub-procedures, graduated nonconvexity (GNC) which realizes a convex relaxation and graduated concavity (GC) which realizes a concave relaxation. It is proved that GNCGCP realizes exactly a type of convex-concave relaxation procedure (CCRP), but with a much simpler formulation without needing convex or concave relaxation in an explicit way. Actually, GNCGCP involves only the gradient of the objective function and is therefore very easy to use in practical applications. Two typical NP-hard problems, (sub)graph matching and quadratic assignment problem (QAP), are employed to demonstrate its simplicity and state-of-the-art performance.

This article reports the advances on the development of mid-infrared integrated optics for stellar interferometry. The devices are fabricated by laser writing techniques on chalcogenide glasses. Laboratory characterizaton is reported and analyzed., Comment: 12 pages, 9 figures, SPIE Astronomical Telescopes and Instrumentation

Estimating intrinsic dimensionality of data is a classic problem in pattern recognition and statistics. Principal Component Analysis (PCA) is a powerful tool in discovering dimensionality of data sets with a linear structure; it, however, becomes ineffective when data have a nonlinear structure. In this paper, we propose a new PCA-based method to estimate intrinsic dimension of data with nonlinear structures. Our method works by first finding a minimal cover of the data set, then performing PCA locally on each subset in the cover and finally giving the estimation result by checking up the data variance on all small neighborhood regions. The proposed method utilizes the whole data set to estimate its intrinsic dimension and is convenient for incremental learning. In addition, our new PCA procedure can filter out noise in data and converge to a stable estimation with the neighborhood region size increasing. Experiments on synthetic and real world data sets show effectiveness of the proposed method., Comment: 8 pages, submitted for publication

Manifold learning is a hot research topic in the field of computer science and has many applications in the real world. A main drawback of manifold learning methods is, however, that there is no explicit mappings from the input data manifold to the output embedding. This prohibits the application of manifold learning methods in many practical problems such as classification and target detection. Previously, in order to provide explicit mappings for manifold learning methods, many methods have been proposed to get an approximate explicit representation mapping with the assumption that there exists a linear projection between the high-dimensional data samples and their low-dimensional embedding. However, this linearity assumption may be too restrictive. In this paper, an explicit nonlinear mapping is proposed for manifold learning, based on the assumption that there exists a polynomial mapping between the high-dimensional data samples and their low-dimensional representations. As far as we know, this is the first time that an explicit nonlinear mapping for manifold learning is given. In particular, we apply this to the method of Locally Linear Embedding (LLE) and derive an explicit nonlinear manifold learning algorithm, named Neighborhood Preserving Polynomial Embedding (NPPE). Experimental results on both synthetic and real-world data show that the proposed mapping is much more effective in preserving the local neighborhood information and the nonlinear geometry of the high-dimensional data samples than previous work.

Isometric feature mapping (Isomap) is a promising manifold learning method. However, Isomap fails to work on data which distribute on clusters in a single manifold or manifolds. Many works have been done on extending Isomap to multi-manifolds learning. In this paper, we first proposed a new multi-manifolds learning algorithm (M-Isomap) with help of a general procedure. The new algorithm preserves intra-manifold geodesics and multiple inter-manifolds edges precisely. Compared with previous methods, this algorithm can isometrically learn data distributed on several manifolds. Secondly, the original multi-cluster manifold learning algorithm first proposed in \cite{DCIsomap} and called D-C Isomap has been revised so that the revised D-C Isomap can learn multi-manifolds data. Finally, the features and effectiveness of the proposed multi-manifolds learning algorithms are demonstrated and compared through experiments.

Describes the application of the Instruction Parsed Corpus as data in the Word Class Drills version 1.0 (WCD v1.0), a simple CALL program teaching word classes or grammatical parts of speech. The WCD v1.0 provides two modes of language learning activities, "viz.", the learning mode and the testing mode. (three references) (Author/CK)