LookupViT: Compressing Visual Information to a Limited Number of Tokens
- 26 October 2024
- book chapter
- Published by Springer Nature
- p. 322-337
Abstract
No abstract availableKeywords
All Related Versions
This publication has 16 references indexed in Scilit:
- FlexiViT: One Model for All Patch Sizes2023
- A unified pruning framework for vision transformersScience China Information Sciences, 2023
- Adaptive Token Sampling for Efficient Vision Transformers2022
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection2022
- LiT: Zero-Shot Transfer with Locked-image text Tuning2022
- CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows2022
- Natural Adversarial Examples2021
- The “Something Something” Video Database for Learning and Evaluating Visual Common Sense2017
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era2017
- ImageNet: A large-scale hierarchical image database2009