8 citations · 24 across the 8 of their papers we have counts for
9 papers
Cached Transformers: Improving Transformers with Differentiable Memory Cache
Zhaoyang Zhang, Wenqi Shao, Yixiao Ge +3
This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiab…
Graph-based Topology Reasoning for Driving Scenes
Tianyu Li, Li Chen, Huijie Wang +10
Understanding the road genome is essential to realize autonomous driving. This highly intelligent problem contains two aspects - the connection relationship of lanes, and the assig…
Real-time Controllable Denoising for Image and Video
Zhaoyang Zhang, Yitong Jiang, Wenqi Shao +4
Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness. In traditional filter-based denoising methods, this c…
Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
Wenqi Shao, Xun Zhao, Yixiao Ge +5
This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because t…
Dynamic Token Normalization Improves Vision Transformers
Wenqi Shao, Yixiao Ge, Zhaoyang Zhang +4
Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual i…
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
Zhang Zhaoyang, Shao Wenqi, Gu Jinwei +2
Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval betw…
ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
Lumin Xu, Yingda Guan, Sheng Jin +5
Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-…
Channel Equilibrium Networks for Learning Deep Representation
Wenqi Shao, Shitao Tang, Xingang Pan +3
Convolutional Neural Networks (CNNs) are typically constructed by stacking multiple building blocks, each of which contains a normalization layer such as batch normalization (BN) a…
SSN: Learning Sparse Switchable Normalization via SparsestMax
Wenqi Shao, Tianjian Meng, Jingyu Li +4
Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new per…