Spike camera mimicking the retina fovea can report per-pixel luminance intensity accumulation by firing spikes. As a bio-inspired vision sensor with high temporal resolution, it has a huge potential for computer vision. However, the sampling model in current Spike camera is so susceptible to quantization and noise that it cannot capture the texture details of objects effectively. In this work, a robust visual sampling model inspired by receptive field (RVSM) is proposed where wavelet filter generated by difference of Gaussian (DoG) and Gaussian filter are used to simulate receptive field. Using corresponding method similar to inverse wavelet transform, spike data from RVSM can be converted into images. To test the performance, we also propose a high-speed motion spike dataset (HMD) including a variety of motion scenes. By comparing reconstructed images in HMD, we find RVSM can improve the ability of capturing information of Spike camera greatly. More importantly, due to mimicking receptive field mechanism to collect regional information, RVSM can filter high intensity noise effectively and improves the problem that Spike camera is sensitive to noise largely. Besides, due to the strong generalization of sampling structure, RVSM is also suitable for other neuromorphic vision sensor. Above experiments are finished in a Spike camera simulator.
FCN+: Global Receptive Convolution Makes FCN Great Again
Institute of Atmospheric Physics, Chinese Academy of Sciences（中国科学院大气物理研究所）；University of Cambridge（剑桥大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Detecting tiny objects is one of the main obstacles hindering the development of object detection. The performance of generic object detectors tends to drastically deteriorate on tiny object detection tasks. In this paper, we point out that either box prior in the anchor-based detector or point prior in the anchor-free detector is sub-optimal for tiny objects. Our key observation is that the current anchor-based or anchor-free label assignment paradigms will incur many outlier tiny-sized ground truth samples, leading to detectors imposing less focus on the tiny objects. To this end, we propose…
UC Berkeley（加州大学伯克利分校）；Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）
Convolutional networks are not aware of an object's geometric variations, which leads to inefficient utilization of model and data capacity. To overcome this issue, recent works on deformation modeling seek to spatially reconfigure the data towards a common arrangement such that semantic recognition suffers less from deformation. This is typically done by augmenting static operators with learned free-form sampling grids in the image space, dynamically tuned to the data and task for adapting the receptive field. Yet adapting the receptive field does not quite reach the actual goal -- what reall…
Many edge and contour detection algorithms give a soft-value as an output and the final binary map is commonly obtained by applying an optimal threshold. In this paper, we propose a novel method to detect image contours from the extracted edge segments of other algorithms. Our method is based on an undirected graphical model with the edge segments set as the vertices. The proposed energy functions are inspired by the surround modulation in the primary visual cortex that help suppressing texture noise. Our algorithm can improve extracting the binary map, because it considers other important fac…
We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. We analyze the effective receptive field in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. …
Beijing Advanced Innovation Center for Big Data and Brain Computing（北京大数据与脑计算高精尖创新中心）；Beihang University（北京航空航天大学）
Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors fulfil real time processing, while their accuracies are often criticized. In this paper, we explore an alternative to build a fast and accurate detector by strengthening lightweight features using a hand-crafted mechanism. Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, whi…
Action recognition is currently one of the top-challenging research fields in computer vision. Convolutional Neural Networks (CNNs) have significantly boosted its performance but rely on fixed-size spatio-temporal windows of analysis, reducing CNNs temporal receptive fields. Among action recognition datasets, egocentric recorded sequences have become of important relevance while entailing an additional challenge: ego-motion is unavoidably transferred to these sequences. The proposed method aims to cope with it by estimating this ego-motion or camera motion. The estimation is used to temporally…
University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions（深港脑科学创新研究院-深圳基础研究机构）；Chengdu University of Traditional Chinese Medicine（成都中医药大学）
Decoding images from brain activity has been a challenge. Owing to the development of deep learning, there are available tools to solve this problem. The decoded image, which aims to map neural spike trains to low-level visual features and high-level semantic information space. Recently, there are a few studies of decoding from spike trains, however, these studies pay less attention to the foundations of neuroscience and there are few studies that merged receptive field into visual image reconstruction. In this paper, we propose a deep learning neural network architecture with biological prope…
Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small perturbations in visual stimuli but the underlying mechanisms that give rise to this robust perception are not understood. In this work, we investigate the role of two biologically plausible mechanisms in adversarial robustness. We demonstrate that the non-uniform sampling performed by the primate retina and the presence of multiple receptive fields with a range of receptive fiel…
Fujian Normal University（福建师范大学）；JOYY AI GROUP（欢聚集团AI团队）；China Design Group Co Ltd（中设集团有限公司）
Image deblurring is a classical computer vision problem that aims to recover a sharp image from a blurred image. To solve this problem, existing methods apply the Encode-Decode architecture to design the complex networks to make a good performance. However, most of these methods use repeated up-sampling and down-sampling structures to expand the receptive field, which results in texture information loss during the sampling process and some of them design the multiple stages that lead to difficulties with convergence. Therefore, our model uses dilated convolution to enable the obtainment of the…
Chongqing University of Technology（重庆理工大学）；University of California（加利福尼亚大学）
Recent advances of Transformers have brought new trust to computer vision tasks. However, on small dataset, Transformers is hard to train and has lower performance than convolutional neural networks. We make vision transformers as data-efficient as convolutional neural networks by introducing multi-focal attention bias. Inspired by the attention distance in a well-trained ViT, we constrain the self-attention of ViT to have multi-scale localized receptive field. The size of receptive field is adaptable during training so that optimal configuration can be learned. We provide empirical evidence t…
In this paper, we present results of processing Dynamic Vision Sensor (DVS) recordings of visual patterns with a retinal model based on foveal-pit inspired Difference of Gaussian (DoG) filters. A DVS sensor was stimulated with varying number of vertical white and black bars of different spatial frequencies moving horizontally at a constant velocity. The output spikes generated by the DVS sensor were applied as input to a set of DoG filters inspired by the receptive field structure of the primate visual pathway. In particular, these filters mimic the receptive fields of the midget and parasol g…
Harbin Institute of Technology（哈尔滨工业大学）；Sun Yat-Sen University（中山大学）
The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has been adopted to address this issue. But it suffers from gridding effect, and the resulting receptive field is only a sparse sampling of input image with checkerboard patterns. In this paper, we present a novel multi-level wavelet CNN (MWCNN) model for better tradeoff between receptive field size and computational efficiency. With the modified U-Net architec…
University of Michigan（密歇根大学）；Google Research（谷歌研究院）
We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive field alignment using a multi-scale architecture that can accommodate extreme variation in action durations; (2) we better exploit the temporal context of actions for both proposal generation and action classification by appropriately extending receptive fields; and (3) we explicitly consider multi-stream feature fusion and demonstrate that fusing motion late i…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Meta Reality Labs Research（Meta现实实验室）
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not context-aware and may under-sample the visual content, and thus adversely impacts both computation efficiency and accuracy. Inspired by the concepts of foveal vision and pre-attentive processing from the human visual perception mechanism, we introduce a novel adaptive spatiotemporal sampling scheme for efficient action recognition. Our system pre-scans the global sc…
Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
Huanjiang Laboratory, Zhuji, P.R. China and School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, P.R.China（湖南江实验室，浙江诸暨，中国 和 浙江大学航空宇航学院，杭州，中国）；School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, P.R.China（浙江大学航空宇航学院，杭州，中国）；Electrical and Computer Engineering Department, Hellenic Mediterranean University, Heraklion, Crete, Greece（希腊地中海大学电气与计算机工程系，赫拉克利翁，克里特，希腊）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Baidu, Inc.（百度公司）
With the rapid development of deep convolutional neural network, face detection has made great progress in recent years. WIDER FACE dataset, as a main benchmark, contributes greatly to this area. A large amount of methods have been put forward where PyramidBox designs an effective data augmentation strategy (Data-anchor-sampling) and context-based module for face detector. In this report, we improve each part to further boost the performance, including Balanced-data-anchor-sampling, Dual-PyramidAnchors and Dense Context Module. Specifically, Balanced-data-anchor-sampling obtains more uniform s…
Imperial College London（帝国理工学院）；Fudan University（复旦大学）
Dilated convolutions are widely used in deep semantic segmentation models as they can enlarge the filters' receptive field without adding additional weights nor sacrificing spatial resolution. However, as dilated convolutional filters do not possess positional knowledge about the pixels on semantically meaningful contours, they could lead to ambiguous predictions on object boundaries. In addition, although dilating the filter can expand its receptive field, the total number of sampled pixels remains unchanged, which usually comprises a small fraction of the receptive field's total area. Inspir…
Peking University（北京大学）；University of Leicester（莱斯特大学）；Karolinska Institutet（卡罗林斯卡学院）
Photoreceptors in the retina are coupled by electrical synapses called "gap junctions". It has long been established that gap junctions increase the signal-to-noise ratio of photoreceptors. Inspired by electrically coupled photoreceptors, we introduced a simple filter, the PR-filter, with only one variable. On BSD68 dataset, PR-filter showed outstanding performance in SSIM during blind denoising tasks. It also significantly improved the performance of state-of-the-art convolutional neural network blind denosing on non-Gaussian noise. The performance of keeping more details might be attributed …
Harbin Institute of Technology（哈尔滨工业大学）；Changzhi University（长治学院）
In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further operations such as features extraction and analysis. Recently, dilated filter has been proposed to trade off between receptive field size and efficiency. But the accompanying gridding effect can cause a sparse sampling of input images with checkerboard patterns. To address this problem, in this paper, we propose a novel multi-level wavelet CNN (MWCNN) model to ach…
We propose a framework inspired by biological vision systems to produce saliency maps of digital images. Well-known computational models for receptive fields of areas in the visual cortex that are specialized for color and orientation perception are used. To model the connectivity between these areas we use the CARLsim library which is a spiking neural network(SNN) simulator. The spikes generated by CARLsim, then serve as extracted features and input to our saliency detection algorithm. This new method of saliency detection is described and applied to benchmark images.
University of Chinese Academy of Sciences（中国科学院大学）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；TuSimple（图森未来）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to spec…
RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School（先进医学计算与分析中心，麻省总医院和哈佛医学院）；Department of Industrial Engineering, University of Pittsburgh（工业工程系，匹兹堡大学）；School of Engineering and Applied Sciences, Harvard University（工程与应用科学学院，哈佛大学）
Sun Yat-Sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）
As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational cost. Another branch of Vision Transformers exploits local attention inspired by CNNs, which only models the interactions between patches in small neighborhoods. Although such a solution reduces the computational cost, it naturally suffers from small attended receptive fields, which may limit the performance. In this work, we explore effective Vision Transformers to pursue a pref…
Tsinghua University（清华大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions. During sampling, residual learning is introduced to ease training and an attention mechanism is applied to fuse features from different samples. Such multiple samples enlarge the kernels' receptive fields significantly without requiring more parameters. While LS-DFN inherits the advantages of DFN, namely avoiding feature map blurring by position-wise kernels while keeping translation i…
Conventional frame-based camera is not able to meet the demand of rapid reaction for real-time applications, while the emerging dynamic vision sensor (DVS) can realize high speed capturing for moving objects. However, to achieve visual texture reconstruction, DVS need extra information apart from the output spikes. This paper introduces a fovea-like sampling method inspired by the neuron signal processing in retina, which aims at visual texture reconstruction only taking advantage of the properties of spikes. In the proposed method, the pixels independently respond to the luminance changes wit…
Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over keys/values to dramatically reduce the computational cost. In this work, we argue that such over-aggressive down-sampling design is not invertible and inevitably causes information dropping especially for high-frequency components in objects (e.g., texture details). Motivated by the wavelet theory, we…
Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
INESC-ID；Instituto Superior Técnico（理工学院）；Universidade de Lisboa（里斯本大学）；Breast Cancer Research Program（乳腺癌研究计划）；Champalimaud Foundation（恰帕拉马德基金会）；Faculdade de Medicina de Lisboa（里斯本医学院）
