1.2k citations · 2.4k across the 41 of their papers we have counts for
14 papers · 1 filter
Attention Spiking Neural Networks
Man Yao, Guangshe Zhao, Hengyu Zhang +5
Benefiting from the event-driven and sparse spiking characteristics of the brain, spiking neural networks (SNNs) are becoming an energy-efficient alternative to artificial neural n…
ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
Yihan Lin, Wei Ding, Shaohua Qiang +2
With event-driven algorithms, especially the spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream-dat…
Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
Yang Wu, Dingheng Wang, Xiaotong Lu +4
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence.…
Temporal-wise Attention Spiking Neural Networks for Event Streams Classification
Man Yao, Huanhuan Gao, Guangshe Zhao +4
How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is o…
Augmenting Anchors by the Detector Itself
Xiaopei Wan, Guoqiu Li, Yujiu Yang +1
Usually, it is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine an…
Restoring Negative Information in Few-Shot Object Detection
Yukuan Yang, Fangyun Wei, Miaojing Shi +1
Few-shot learning has recently emerged as a new challenge in the deep learning field: unlike conventional methods that train the deep neural networks (DNNs) with a large number of…
Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs
Dingheng Wang, Bijiao Wu, Guangshe Zhao +5
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, since the modern RNNs, i…
Hybrid Tensor Decomposition in Neural Network Compression
Bijiao Wu, Dingheng Wang, Guangshe Zhao +2
Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level feature…
Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
Weihua He, YuJie Wu, Lei Deng +6
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion. Sp…
Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Faqiang Liu, Mingkun Xu, Guoqi Li +3
Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability. Despite many training strategies proposed to improve tra…
Compressing 3DCNNs Based on Tensor Train Decomposition
Dingheng Wang, Guangshe Zhao, Guoqi Li +2
Three dimensional convolutional neural networks (3DCNNs) have been applied in many tasks, e.g., video and 3D point cloud recognition. However, due to the higher dimension of convol…
DashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object Tracking
Zheyu Yang, Yujie Wu, Guanrui Wang +5
Computer-science-oriented artificial neural networks (ANNs) have achieved tremendous success in a variety of scenarios via powerful feature extraction and high-precision data opera…
Crossbar-aware neural network pruning
Ling Liang, Lei Deng, Yueling Zeng +5
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operati…
Super-resolution of spatiotemporal event-stream image captured by the asynchronous temporal contrast vision sensor
Hongmin Li, Guoqi Li, Hanchao Liu +1
Super-resolution (SR) is a useful technology to generate a high-resolution (HR) visual output from the low-resolution (LR) visual inputs overcoming the physical limitations of the…