Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number of tokens may not be necessary, as not all tokens are equally important. In this paper, we investigate token pruning to accelerate inference for object detection and instance segmentation, extending prior works from image classification. Through extensive experiments, we offer four insights for dense tasks: (i) tokens should not be completely pruned and discarded, but rather preserved in the feature maps for later use. (ii) reactivating previously pruned tokens can further enhance model performance. (iii) a dynamic pruning rate based on images is better than a fixed pruning rate. (iv) a lightweight, 2-layer MLP can effectively prune tokens, achieving accuracy comparable with complex gating networks with a simpler design. We evaluate the impact of these design choices on COCO dataset and present a method integrating these insights that outperforms prior art token pruning models, significantly reducing performance drop from ~1.5 mAP to ~0.3 mAP for both boxes and masks. Compared to the dense counterpart that uses all tokens, our method achieves up to 34% faster inference speed for the whole network and 46% for the backbone.

翻译：暂无翻译