Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (7) , 8360-8368
Abstract
Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference, while time-consuming training is still unavoidable. In contrast, this paper points out that the million-scale training data is redundant, which is the fundamental reason for the tedious training. To address the issue, this paper aims to introduce sparsity into data and proposes an end-to-end efficient training framework from three sparse perspectives, dubbed Tri-Level E-ViT. Specifically, we leverage a hierarchical data redundancy reduction scheme, by exploring the sparsity under three levels: number of training examples in the dataset, number of patches (tokens) in each example, and number of connections between tokens that lie in attention weights. With extensive experiments, we demonstrate that our proposed technique can noticeably accelerate training for various ViT architectures while maintaining accuracy. Remarkably, under certain ratios, we are able to improve the ViT accuracy rather than compromising it. For example, we can achieve 15.2% speedup with 72.6% (+0.4) Top-1 accuracy on Deit-T, and 15.7% speedup with 79.9% (+0.1) Top-1 accuracy on Deit-S. This proves the existence of data redundancy in ViT. Our code is released at https://github.com/ZLKong/Tri-Level-ViTKeywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision TransformerProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Masked Autoencoders Are Scalable Vision Learners2022
- An End-to-End Transformer Model for 3D Object Detection2021
- SwinIR: Image Restoration Using Swin Transformer2021
- PCT: Point cloud transformerComputational Visual Media, 2021
- T6D-Direct: Transformers for Multi-object 6D Pose Direct Regression2021