Search

Oriented object detection in aerial images is a crucial link in earth observation. As a special parameter in oriented object representation, the angle is the key to achieving high-precision detection. However, the widely used regression-based methods suffer from boundary discontinuity problems due to the periodicity of the angle. To address this issue, we proposed a novel angle prediction method called fixed step trigonometric coder (FSTC). Exploiting the innate periodicity of trigonometric functions, FSTC can encode angles cyclically in a succinct, continuous, and uniform manner. Based on FSTC, we designed a single-shot oriented object detector, namely, a trigonometric-coded refined detector (TRDet), for high-precision object detection in real-time. TRDet consists of two modules: the anchor optimization module (AOM) and the object detection module (ODM). AOM employs FSTC to generate high-quality rotated anchors. In ODM, a dynamically weighted loss (DWL) was proposed to make the model focus on hard samples with higher angle deviation. Extensive experiments on DOTA and HRSC2016 show that both FSTC and TRDet can achieve competitive performance compared with peer works. [ABSTRACT FROM AUTHOR]

In this article, we propose BNAS-v2 to further improve the efficiency of broad neural architecture search (BNAS), which employs a broad convolutional neural network (BCNN) as the search space. In BNAS, the single-path sampling-updating strategy of an overparameterized BCNN leads to terrible unfair training issue, which restricts the efficiency improvement. To mitigate the unfair training issue, we employ a continuous relaxation strategy to optimize all paths of the overparameterized BCNN simultaneously. However, continuous relaxation leads to a performance collapse issue that leads to the unsatisfactory performance of the learned BCNN. For that, we propose the confident learning rate (CLR) and introduce the combination of partial channel connections and edge normalization. Experimental results show that 1) BNAS-v2 delivers state-of-the-art search efficiency on both CIFAR-10 (0.05 GPU days, which is $4\times $ faster than BNAS) and ImageNet (0.19 GPU days) with better or competitive performance; 2) the above two solutions are effectively alleviating the performance collapse issue; and 3) BNAS-v2 achieves powerful generalization ability on multiple transfer tasks, e.g., MNIST, FashionMNIST, NORB, and SVHN. The code is available at https://github.com/zixiangding/BNASv2 . [ABSTRACT FROM AUTHOR]

For a typical Scene Graph Generation (SGG) method in image understanding, there usually exists a large gap in the performance of the predicates’ head classes and tail classes. This phenomenon is mainly caused by the semantic overlap between different predicates as well as the long-tailed data distribution. In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above problems by taking the correlation between predicates into consideration. To measure the semantic overlap between highly correlated predicate classes, a Predicate Correlation Matrix (PCM) is defined to quantify the relationship between predicate pairs, which is dynamically updated to remove the matrix’s long-tailed bias. In addition, PCM is integrated into a predicate correlation loss function ($L_{PC}$) to reduce discouraging gradients of unannotated classes. The proposed method is evaluated on several benchmarks, where the performance of the tail classes is significantly improved when built on existing methods. [ABSTRACT FROM AUTHOR]

Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network. To quantify visual distortion, the perceptual distance between the adversarial example and the original image, is introduced in our loss. We first approximate the gradient of the corresponding non-differentiable loss function by sampling noise from the learned noise distribution. Then the distribution is updated using the estimated gradient to reduce visual distortion. The learning continues until an adversarial example is found. We validate the effectiveness of our attack on ImageNet. Our attack results in much lower distortion when compared to the state-of-the-art black-box attacks and achieves 100% success rate on InceptionV3, ResNet50 and VGG16bn. Furthermore, we theoretically prove the convergence of our model. The code is publicly available at https://github.com/Alina-1997/visual-distortion-in-attack. [ABSTRACT FROM AUTHOR]

Spatial–temporal action detection in videos is a challenging problem that has attracted considerable attention in recent years. Most current approaches address action detection as an object detection problem, which utilizes successful object detection frameworks such as Faster R-CNN to operate action detection at every single frame first, and then generates action tubes by linking bounding boxes across the whole video in an offline fashion. However, unlike object detection in static images, temporal context information is vital for action detection in videos. Therefore, we propose an online action detection model that leverages the spatial–temporal context information existing in videos to perform action inference and localization. More specifically, we try to depict the spatial–temporal context pattern of actions via an encoder–decoder model that is based on a convolutional recurrent neural network. The model accepts a video snippet as input and encodes the dynamic information inside the snippet in the forward pass. During the backward pass, the decoder resolves the information for action detection with the current appearance or motion cue at each time stamp. In addition, we devise an incremental action-tube construction algorithm that enables our model to accomplish action prediction ahead of time and performs action detection in an online fashion. To evaluate the performance of our method, we conduct experiments on three popular public datasets UCF-101, UCF-Sports, and J-HMDB-21. The experimental results demonstrate that our method can achieve competitive or superior performance when compared to the state-of-the-art methods. To encourage further research, we release our project on “ https://github.com.hjjpku.OATD.” [ABSTRACT FROM AUTHOR]

This paper demonstrates a novel nanofabrication technology for producing high-density gated molybdenum (Mo) field-emitter array (FEA) based on modified nanosphere lithography (NSL). The arc-shaped side wall of gate apertures introduced by the conventional NSL process put obstacles in the formation of sharp cone-type emitters. In this paper, a two-method solution was employed to facilitate the realization of gate apertures with sharper cutting side wall which are beneficial for the formation of sharper gated Mo emitters. One method was softening nanosphere to enlarge the contact area between nanosphere and substrate. The other was optimizing gate film deposition conditions to dramatically reduce the diffraction effects. Due to the improvements in the geometrical shape of gated Mo emitters, a low-voltage working high-density gated Mo FEA was demonstrated in this paper. This is the first observation of remarkable electron emission from high-density gated Mo FEA fabricated using such as low-cost, high-throughput, and high-efficiency technique which is expected to substantially overcome the challenges in the traditional fabrication process and promotes the low-cost and large-area application of high-density gated field-emitter devices. In addition, the novel nanofabricating method is expected to offer a simple and scalable route which allows fabrication of many gated field-emission devices. [ABSTRACT FROM AUTHOR]

Informative and discriminative feature descriptors are vital in qualitative and quantitative shape analysis for a large variety of graphics applications. Conventional feature descriptors primarily concentrate on discontinuity of certain differential attributes at different orders that naturally give rise to their discriminative power in depicting point, line, small patch features, etc. This paper seeks novel strategies to define generalized, user-specified features anywhere on shapes. Our new region-based feature descriptors are constructed primarily with the powerful spectral graph wavelets (SGWs) that are both multi-scale and multi-level in nature, incorporating both local (differential) and global (integral) information. To our best knowledge, this is the first attempt to organize SGWs in a hierarchical way and unite them with the bi-harmonic diffusion field towards quantitative region-based shape analysis. Furthermore, we develop a local-to-global shape feature detection framework to facilitate a host of graphics applications, including partial matching without point-wise correspondence, coarse-to-fine recognition, model recognition, etc. Through the extensive experiments and comprehensive comparisons with the state-of-the-art, our framework has exhibited many attractive advantages such as being geometry-aware, robust, discriminative, isometry-invariant, etc. [ABSTRACT FROM AUTHOR]

We demonstrate edge electron emission from flexible free-standing graphene paper (GP). The turn-on field is measured at 2.2 V/ \mum , and the maximum emission current density at 3 A/cm^2 . The field emission properties of GP can be optimized by adjusting the thickness and annealing temperature. Because it is flexible, it can be shaped into different forms to meet the requirements of specific applications. The electron beam shape can range from a sheet electron beam to a cylindrical (hollow) electron beam. [ABSTRACT FROM AUTHOR]

Most unconstrained facial expression recognition (FER) methods take original facial images as inputs to learn discriminative features by well-designed loss functions, which cannot reflect important visual information in faces. Although existing methods have explored the visual information of constrained facial expressions, there is no explicit modeling of what visual information is important for unconstrained FER. To find out valuable information of unconstrained facial expressions, we pose a new problem of no-reference de-elements learning: we decompose any unconstrained facial image into the facial expression element and a neutral face without the reference of corresponding neutral faces. Importantly, the element provides visualization results to understand important facial expression information and improves the discriminative power of features. Moreover, we propose a simple yet effective De-Elements Network (DENet) to learn the element and introduce appropriate constraints to overcome no ground truth of corresponding neutral faces during the de-elements learning. We extensively evaluate the proposed method on in-the-wild FER datasets including RAF-DB, AffectNet, SFEW and FERPlus. The comparable results show that our method is promising to improve classification performance and achieves equivalent performance compared with state-of-the-art methods. Also, we demonstrate the strong generalization performance on realistic occlusion and pose variation datasets and the cross-dataset evaluation. [ABSTRACT FROM AUTHOR]

Existing facial expression recognition (FER) methods train encoders with different large-scale training data for specific FER applications. In this paper, we propose a new task in this field. This task aims to pre-train a general encoder to extract any facial expression representations without fine-tuning. To tackle this task, we extend the self-supervised contrastive learning to pre-train a general encoder for facial expression analysis. To be specific, given a batch of facial expressions, some positive and negative pairs are firstly constructed based on coarse-grained labels and a FER-specified data augmentation strategy. Secondly, we propose the coarse-contrastive (CRS-CONT) learning, where the features of positive pairs are pulled together, while pushed away from the features of negative pairs. Moreover, one key event is that the excessive constraint on the coarse-grained feature distribution will affect fine-grained FER applications. To address this, a weight vector is designed to control the optimization of the CRS-CONT learning. As a result, a well-trained general encoder with frozen weights could preferably adapt to different facial expressions and realize the linear evaluation on any target datasets. Extensive experiments on both in- the-wild and in- the-lab FER datasets show that our method provides superior or comparable performance against state-of-the-art FER methods, especially on unseen facial expressions and cross-dataset evaluation. We hope that this work will help to reduce the training burden and develop a new solution against the fully-supervised feature learning with fine-grained labels. Code and the general encoder will be publicly available at https://github.com/hangyu94/CRS-CONT [ABSTRACT FROM AUTHOR]

Facial expression recognition is of significant importance in criminal investigation and digital entertainment. Under unconstrained conditions, existing expression datasets are highly class-imbalanced, and the similarity between expressions is high. Previous methods tend to improve the performance of facial expression recognition through deeper or wider network structures, resulting in increased storage and computing costs. In this paper, we propose a new adaptive supervised objective named AdaReg loss, re-weighting category importance coefficients to address this class imbalance and increasing the discrimination power of expression representations. Inspired by human beings’ cognitive mode, an innovative coarse-fine (C-F) labels strategy is designed to guide the model from easy to difficult to classify highly similar representations. On this basis, we propose a novel training framework named the emotional education mechanism (EEM) to transfer knowledge, composed of a knowledgeable teacher network (KTN) and a self-taught student network (STSN). Specifically, KTN integrates the outputs of coarse and fine streams, learning expression representations from easy to difficult. Under the supervision of the pre-trained KTN and existing learning experience, STSN can maximize the potential performance and compress the original KTN. Extensive experiments on public benchmarks demonstrate that the proposed method achieves superior performance compared to current state-of-the-art frameworks with 88.07% on RAF-DB, 63.97% on AffectNet and 90.49% on FERPlus. [ABSTRACT FROM AUTHOR]

Face sketch synthesis from a photo is of significant importance in digital entertainment. An intelligent face sketch synthesis system requires a strong robustness to lighting variations. Under uncontrolled lighting conditions in real-world settings, such a system will perform consistently well and have little restriction on the lighting conditions. However, previous face sketch synthesis methods tend to synthesize sketches under well-controlled lighting conditions. These methods are sensitive to lighting variations and produce unsatisfactory results when the lighting condition varies. In this paper, we propose a novel cascaded face sketch synthesis framework composed of a multiple feature generator and a cascaded low-rank representation. The multiple feature generator not only produces a generated sketch feature consistent with an artist’s drawing style but also extracts a photo feature that is robust to various illuminations. Both features ensure that given a photo patch, the optimal sketch candidates can be selected from the database. The cascaded low-rank representation enables a gradual reduction in the gap between the synthesized face sketch and the corresponding artist-drawn sketch. Experimental results illustrate that the proposed cascaded framework generates realistic sketches on par with the current methods on the Chinese University of Hong Kong face sketch database under well-controlled illuminations. Moreover, this framework exhibits greatly improved performance compared to these methods on the extended Chinese University of Hong Kong face sketch database and Chinese celebrity face photos from the web under different illuminations. We argue that this framework paves a novel way for the implementation of computer-aided optical systems that are of essential importance in both face sketch synthesis and optical imaging. [ABSTRACT FROM AUTHOR]