90 citations · 271 across the 49 of their papers we have counts for
7 papers · 1 filter
StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloud
Weichao Wang, Wendong Mao, Zhongfeng Wang
The deployment of high-accuracy 3D object detection models from point cloud remains a significant challenge due to their substantial computational and memory requirements. To addre…
A Memory-Efficient Framework for Deformable Transformer with Neural Architecture Search
Wendong Mao, Mingfan Zhao, Jianfeng Guan +2
Deformable Attention Transformers (DAT) have shown remarkable performance in computer vision tasks by adaptively focusing on informative image regions. However, their data-dependen…
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
Huihong Shi, Haikuo Shao, Wendong Mao +1
Motivated by the huge success of Transformers in the field of natural language processing (NLP), Vision Transformers (ViTs) have been rapidly developed and achieved remarkable perf…
S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution
Minghao She, Wendong Mao, Huihong Shi +1
Nowadays, deep learning based methods have demonstrated impressive performance on ideal super-resolution (SR) datasets, but most of these methods incur dramatically performance dro…
ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention
Jyotikrishna Dass, Shang Wu, Huihong Shi +4
Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention…
Learning Robust and Lightweight Model through Separable Structured Transformations
Xian Wei, Yanhui Huang, Yangyu Xu +5
With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are…
Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm
Haonan Wang, Jun Lin, Zhongfeng Wang
Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion abilit…