GLiT: Neural Architecture Search for Global and Local Image Transformer

Boyu Chen, Peixia Li, Chuming Li, Baopu Li, Lei Bai, Chen Lin, Ming Sun, Junjie Yan, Wanli Ouyang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 12-21

Abstract


We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image recognition. However, the transformer is designed for NLP tasks and thus could be sub-optimal when directly used for image recognition. In order to improve the visual representation ability for transformers, we propose a new search space and searching algorithm. Specifically, we introduce a locality module that models the local correlations in images explicitly with fewer computational cost. With the locality module, our search space is defined to let the search algorithm freely trade off between global and local information as well as optimizing the low-level design choice in each module. To tackle the problem caused by huge search space, a hierarchical neural architecture search method is proposed to search the optimal vision transformer from two levels separately with the evolutionary algorithm. Extensive experiments on the ImageNet dataset demonstrate that our method can find more discriminative and efficient transformer variants than the ResNet family (e.g., ResNet101) and the baseline ViT for image classification.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2021_ICCV, author = {Chen, Boyu and Li, Peixia and Li, Chuming and Li, Baopu and Bai, Lei and Lin, Chen and Sun, Ming and Yan, Junjie and Ouyang, Wanli}, title = {GLiT: Neural Architecture Search for Global and Local Image Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {12-21} }