Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation
원문 초록
Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs and outputs usually imply more tokens involved in computations. Directly removing the less attentive tokens has been discussed for the image classification task but can not be extended to semantic segmentation since a dense prediction is required for every patch. To this end, this work introduces a Dynamic Token Pruning (DToP) method based on the early exit of tokens for semantic segmentation. Motivated by the coarse-to-fine segmentation process by humans, we naturally split the widely adopted auxiliary-loss-based network architecture into several stages, where each auxiliary block grades every token's difficulty level. We can finalize the prediction of easy tokens in advance without completing the entire forward pass. Moreover, we keep $k$ highest confidence tokens for each semantic category to uphold the representative context information. Thus, computational complexity will change with the difficulty of the input, akin to the way humans do segmentation. Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks
Admissibility of Stein Shrinkage for Batch Normalization in the Presence of Adversarial Attacks
A Robust Feature Downsampling Module for Remote Sensing Visual Tasks
Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
토론
이 논문과 연결된 포럼 글이 아직 없습니다.