1 code implementation • 6 Nov 2023 • Xuwei Xu, Sen Wang, Yudong Chen, Yanping Zheng, Zhewei Wei, Jiajun Liu
Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands.
Ranked #187 on Image Classification on ImageNet
1 code implementation • 26 Oct 2023 • Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Brano Kusy, Zi Huang
Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance.
1 code implementation • 9 Oct 2023 • Xuwei Xu, Changlin Li, Yudong Chen, Xiaojun Chang, Jiajun Liu, Sen Wang
By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages.
no code implementations • 9 Oct 2023 • Xuwei Xu, Sen Wang, Yudong Chen, Jiajun Liu
Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups.
1 code implementation • 27 Oct 2022 • Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Zi Huang
Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features.