arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.01035cs.CVcs.LG
收藏

加速大规模视觉Transformer实现无微调稠密预测

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

Peking University(北京大学);Microsoft Research Asia(微软亚洲研究院);ETH Zurich(苏黎世联邦理工学院)

Weicong Liang, Yuhui Yuan, Henghui Ding, Xiao Luo, Weihong Lin, Ding Jia, Zheng Zhang, Chao Zhang, Han Hu

摘要:

视觉Transformer最近在各种视觉任务中取得了有竞争力的结果,但在处理大量令牌时仍然存在计算成本高的问题。已经开发了许多先进的方法来减少大规模视觉Transformer中的标记总数,特别是对于图像分类任务。通常情况下,他们根据与类标记的相关性选择一小组基本标记,然后微调视觉Transformer的权重。由于计算和GPU存储器成本比图像分类重得多,这种微调对于密集预测不太实用。在本文中,我们专注于一个更具挑战性的问题,即,加速大规模视觉Transformer的密集预测,而无需任何额外的重新训练或微调。针对高分辨率表示对于密集预测是必要的这一事实,我们提出了两个非参数算子,一个令牌聚类层以减少令牌的数量,一个令牌重构层以增加令牌的数量。执行以下步骤来实现这一点:(i)我们使用令牌聚类层将相邻令牌聚类在一起,从而产生维持空间结构的低分辨率表示;(ii)我们仅将以下Transformer层应用于这些低分辨率表示或聚类的令牌;以及(iii)我们使用令牌重构层来从细化的低分辨率表示重新创建高分辨率表示。通过我们的方法获得的结果是有前途的五个密集的预测任务,包括目标检测,语义分割,全景分割,实例分割,和深度估计。

英文摘要:

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the class token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, i.e., accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a token clustering layer to decrease the number of tokens and a token reconstruction layer to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks, including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑