Skip to yearly menu bar Skip to main content


Poster

A General and Efficient Training for Transformer via Token Expansion

Wenxuan Huang · Yunhang Shen · Jiao Xie · Baochang Zhang · Gaoqi He · Ke Li · Xing Sun · Shaohui Lin

Arch 4A-E Poster #113
[ ] [ Paper PDF ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT

Abstract:

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping.Meanwhile, they break the training consistency of the original transformers, including the consistency of hyper-parameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an ``initialization-expansion-merging'' pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyper-parameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3x faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines.

Chat is not available.