Which Tokens to Use? Investigating Token Reduction in Vision Transformers-Reference-Cited by-同舟云学术

Which Tokens to Use? Investigating Token Reduction in Vision Transformers

Published:2023-10-02 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
language:
Short-container-title:

Author:

Haurum Joakim Bruslund¹,Escalera Sergio²,Taylor Graham W.³,Moeslund Thomas B.¹

Affiliation:

1. Aalborg University & Pioneer Centre for AI,Visual Analysis and Perception (VAP) Laboratory,Denmark

2. Universitat de Barcelona & Computer Vision Center,Spain

3. University of Guelph & Vector Institute for AI,Canada

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10350357/10350360/10350983.pdf?arnumber=10350983

Reference66 articles.

1. VATT: Transformers for multimodal self-supervised learning from raw video, audio and text;Akbari;Advances in Neural Information Processing Systems,2021

2. FlexiViT: One Model for All Patch Sizes

3. Token merging: Your vit but faster;Bolya

4. What Do Different Evaluation Metrics Tell Us About Saliency Models?

5. Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. BSViT: A Bit-Serial Vision Transformer Accelerator Exploiting Dynamic Patch and Weight Bit-Group Quantization;IEEE Transactions on Circuits and Systems I: Regular Papers;2024-09

2. Conditional computation in neural networks: Principles and research trends;Intelligenza Artificiale;2024-07-31

3. DRVMon-VM: Distracted driver recognition using large pre-trained video transformers;2024 IEEE Intelligent Vehicles Symposium (IV);2024-06-02

4. Lightweight ViT Convolutional Embedding Module Based on Super-Token Clustering;Journal of Digital Contents Society;2024-02-28

5. Remote Sensing Scene Classification via Second-Order Differentiable Token Transformer Network;IEEE Transactions on Geoscience and Remote Sensing;2024