Make A Long Image Short: Adaptive Token Length for Vision Transformers

no code implementations • 3 Dec 2021 • Yichen Zhu, Yuqin Zhu, Jie Du, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference.

Action Recognition Image Classification

Training BatchNorm Only in Neural Architecture Search and Beyond

no code implementations • 1 Dec 2021 • Yichen Zhu, Jie Du, Yuqin Zhu, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet.

Fairness Neural Architecture Search