arXiv:2406.08816

ToSA: Token Selective Attention for Efficient Vision Transformers

Manish Kumar Singh, Rajeev Yasarla, Hong Cai, Mingu Lee, Fatih Porikli

제출 2024-06-13

원문 초록

In this paper, we propose a novel token selective attention approach, ToSA, which can identify tokens that need to be attended as well as those that can skip a transformer layer. More specifically, a token selector parses the current attention maps and predicts the attention maps for the next layer, which are then used to select the important tokens that should participate in the attention operation. The remaining tokens simply bypass the next layer and are concatenated with the attended ones to re-form a complete set of tokens. In this way, we reduce the quadratic computation and memory costs as fewer tokens participate in self-attention while maintaining the features for all the image patches throughout the network, which allows it to be used for dense prediction tasks. Our experiments show that by applying ToSA, we can significantly reduce computation costs while maintaining accuracy on the ImageNet classification benchmark. Furthermore, we evaluate on the dense prediction task of monocular depth estimation on NYU Depth V2, and show that we can achieve similar depth prediction accuracy using a considerably lighter backbone with ToSA.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2505.10565공통 태그 Prediction, Depth Estimation, Monocular Depth Estimation, Depth Prediction

Depth Anything with Any Prior

토론

이 논문과 연결된 포럼 글이 아직 없습니다.