Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention

28 September 2022

Papers citing "Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention"

24 / 24 papers shown

Title
DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs Zehao Wang Senthil Purushwalkam Caiming Xiong Siyang Song Chenhui Xu Ran Xu 123 2 0 23 Apr 2025
Unified Visual Transformer Compression Shixing Yu Tianlong Chen Jiayi Shen Huan Yuan Jianchao Tan Sen Yang Ji Liu Zhangyang Wang ViT 41 93 0 15 Mar 2022
A ConvNet for the 2020s Zhuang Liu Hanzi Mao Chaozheng Wu Christoph Feichtenhofer Trevor Darrell Saining Xie ViT 128 5,137 0 10 Jan 2022
AdaViT: Adaptive Tokens for Efficient Vision Transformer Hongxu Yin Arash Vahdat J. Álvarez Arun Mallya Jan Kautz Pavlo Molchanov ViT 79 335 0 14 Dec 2021
Learned Token Pruning for Transformers Sehoon Kim Sheng Shen D. Thorsley A. Gholami Woosuk Kwon Joseph Hassoun Kurt Keutzer 48 154 0 02 Jul 2021
IA-RED $^2$ : Interpretability-Aware Redundancy Reduction for Vision Transformers Bowen Pan Yikang Shen Yi Ding Zhangyang Wang Rogerio Feris A. Oliva VLM ViT 82 160 0 23 Jun 2021
Chasing Sparsity in Vision Transformers: An End-to-End Exploration Tianlong Chen Yu Cheng Zhe Gan Lu Yuan Lei Zhang Zhangyang Wang ViT 60 221 0 08 Jun 2021
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Yongming Rao Wenliang Zhao Benlin Liu Jiwen Lu Jie Zhou Cho-Jui Hsieh ViT 76 697 0 03 Jun 2021
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Enze Xie Wenhai Wang Zhiding Yu Anima Anandkumar J. Álvarez Ping Luo ViT 242 4,990 0 31 May 2021
All Tokens Matter: Token Labeling for Training Better Vision Transformers Zihang Jiang Qibin Hou Li-xin Yuan Daquan Zhou Yujun Shi Xiaojie Jin Anran Wang Jiashi Feng ViT 61 208 0 22 Apr 2021
Vision Transformer Pruning Mingjian Zhu Yehui Tang Kai Han ViT 49 91 0 17 Apr 2021
Going deeper with Image Transformers Hugo Touvron Matthieu Cord Alexandre Sablayrolles Gabriel Synnaeve Hervé Jégou ViT 133 1,006 0 31 Mar 2021
CvT: Introducing Convolutions to Vision Transformers Haiping Wu Bin Xiao Noel Codella Mengchen Liu Xiyang Dai Lu Yuan Lei Zhang ViT 134 1,901 0 29 Mar 2021
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo Ling Shao ViT 493 3,709 0 24 Feb 2021
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers Sixiao Zheng Jiachen Lu Hengshuang Zhao Xiatian Zhu Zekun Luo ... Yanwei Fu Jianfeng Feng Tao Xiang Philip Torr Li Zhang ViT 178 2,893 0 31 Dec 2020
Deformable DETR: Deformable Transformers for End-to-End Object Detection Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang Jifeng Dai ViT 200 5,046 0 08 Oct 2020
End-to-End Object Detection with Transformers Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov Sergey Zagoruyko ViT 3DV PINN 353 13,002 0 26 May 2020
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Mingxing Tan Quoc V. Le 3DV MedIm 129 18,058 0 28 May 2019
Are Sixteen Heads Really Better than One? Paul Michel Omer Levy Graham Neubig MoE 97 1,060 0 25 May 2019
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Jonathan Frankle Michael Carbin 208 3,457 0 09 Mar 2018
Learning Efficient Convolutional Networks through Network Slimming Zhuang Liu Jianguo Li Zhiqiang Shen Gao Huang Shoumeng Yan Changshui Zhang 122 2,418 0 22 Aug 2017
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression Jian-Hao Luo Jianxin Wu Weiyao Lin 52 1,760 0 20 Jul 2017
Pruning Filters for Efficient ConvNets Hao Li Asim Kadav Igor Durdanovic H. Samet H. Graf 3DPC 188 3,693 0 31 Aug 2016
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding Song Han Huizi Mao W. Dally 3DGS 237 8,821 0 01 Oct 2015