Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Wangbo, Tang, Jiasheng, Han, Yizeng, Song, Yibing, Wang, Kai, Huang, Gao, Wang, Fan, You, Yang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909351833239552
author Zhao, Wangbo
Tang, Jiasheng
Han, Yizeng
Song, Yibing
Wang, Kai
Huang, Gao
Wang, Fan
You, Yang
author_facet Zhao, Wangbo
Tang, Jiasheng
Han, Yizeng
Song, Yibing
Wang, Kai
Huang, Gao
Wang, Fan
You, Yang
contents Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11808
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Zhao, Wangbo
Tang, Jiasheng
Han, Yizeng
Song, Yibing
Wang, Kai
Huang, Gao
Wang, Fan
You, Yang
Computer Vision and Pattern Recognition
Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
title Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.11808