Patch Slimming for Efficient Vision Transformers
This addresses efficiency issues for vision transformer users, offering a significant reduction in computational costs with minimal performance loss, though it is incremental as it builds on existing transformer architectures.
The paper tackles the high computational cost of vision transformers by proposing a patch slimming method that removes less impactful patches in a top-down manner, reducing over 45% FLOPs for ViT-Ti with only a 0.2% accuracy drop on ImageNet.
This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convolutional neural networks, the huge computational cost of vision transformers is still a severe issue. Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a top-down paradigm. We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers. For each layer, the impact of a patch on the final output feature is approximated and patches with less impact will be removed. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers without affecting their performances. For example, over 45% FLOPs of the ViT-Ti model can be reduced with only 0.2% top-1 accuracy drop on the ImageNet dataset.