Image Recognition with Online Lightweight Vision Transformer: A Survey
By: Zherui Zhang , Rongtao Xu , Jie Zhou and more
Potential Business Impact:
Makes computer vision faster and use less power.
The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range dependencies and enable parallel processing, yet lack inductive biases and efficiency benefits, facing significant computational and memory challenges that limit its real-world applicability. This paper surveys various online strategies for generating lightweight vision transformers for image recognition, focusing on three key areas: Efficient Component Design, Dynamic Network, and Knowledge Distillation. We evaluate the relevant exploration for each topic on the ImageNet-1K benchmark, analyzing trade-offs among precision, parameters, throughput, and more to highlight their respective advantages, disadvantages, and flexibility. Finally, we propose future research directions and potential challenges in the lightweighting of vision transformers with the aim of inspiring further exploration and providing practical guidance for the community. Project Page: https://github.com/ajxklo/Lightweight-VIT
Similar Papers
A Novel Lightweight Transformer with Edge-Aware Fusion for Remote Sensing Image Captioning
CV and Pattern Recognition
Makes satellite pictures tell better stories.
Hands-on Evaluation of Visual Transformers for Object Recognition and Detection
CV and Pattern Recognition
Helps computers see the whole picture, not just parts.
Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies
CV and Pattern Recognition
Makes smart computer vision work on small devices.