Learned Thresholds Token Merging and Pruning for Vision Transformers
This work addresses the computational inefficiency of vision transformers for practical deployment in computer vision, representing an incremental improvement over existing token reduction techniques.
The paper tackles the high computational cost of vision transformers by introducing Learned Thresholds token Merging and Pruning (LTMP), which dynamically reduces input tokens; it achieves state-of-the-art accuracy on ImageNet classification across reduction rates with only a single fine-tuning epoch, making it an order of magnitude faster than previous methods.
Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years. However, their high computational costs remain a significant barrier to their practical deployment. In particular, the complexity of transformer models is quadratic with respect to the number of input tokens. Therefore techniques that reduce the number of input tokens that need to be processed have been proposed. This paper introduces Learned Thresholds token Merging and Pruning (LTMP), a novel approach that leverages the strengths of both token merging and token pruning. LTMP uses learned threshold masking modules that dynamically determine which tokens to merge and which to prune. We demonstrate our approach with extensive experiments on vision transformers on the ImageNet classification task. Our results demonstrate that LTMP achieves state-of-the-art accuracy across reduction rates while requiring only a single fine-tuning epoch, which is an order of magnitude faster than previous methods. Code is available at https://github.com/Mxbonn/ltmp .