تقرير
A General and Efficient Training for Transformer via Token Expansion
العنوان: | A General and Efficient Training for Transformer via Token Expansion |
---|---|
المؤلفون: | Huang, Wenxuan, Shen, Yunhang, Xie, Jiao, Zhang, Baochang, He, Gaoqi, Li, Ke, Sun, Xing, Lin, Shaohui |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition |
الوصف: | 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. Code is available at https://github.com/Osilly/TokenExpansion . Comment: Accepted to CVPR 2024. Code is available at https://github.com/Osilly/TokenExpansion |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2404.00672 |
رقم الأكسشن: | edsarx.2404.00672 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |