Searching the Search Space of Vision Transformer
2021
Vision Transformer has shown great visual representation power in substantial
vision tasks such as recognition and detection, and thus been attracting
fast-growing efforts on manually designing more effective architectures. In
this paper, we propose to use neural architecture search to automate this
process, by searching not only the architecture but also the search space. The
central idea is to gradually evolve different search dimensions guided by their
E-T Error computed using a weight-sharing supernet. Moreover, we provide design
guidelines of general vision transformers with extensive analysis according to
the space searching process, which could promote the understanding of vision
transformer. Remarkably, the searched models, named S3 (short for Searching the
Search Space), from the searched space achieve superior performance to recently
proposed models, such as Swin, DeiT and ViT, when evaluated on ImageNet. The
effectiveness of S3 is also illustrated on object detection, semantic
segmentation and visual question answering, demonstrating its generality to
downstream vision and vision-language tasks. Code and models will be available
at https://github.com/microsoft/Cream.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
35
References
0
Citations
NaN
KQI