Abstract
Modeling visual data as tokens (i.e., image patches), and applying attention mechanisms or feed-forward networks on top of them has shown to be highly effective in recent years. The common pipeline in such approaches includes a tokenization method, followed by a set of layers/blocks for information mixing, both within tokens and among tokens. In common practice, image patches are flattened when converted into tokens, discarding the spatial structure within each patch. Next, a module such as multi-head self-attention captures the pairwise relations among the tokens and mixes them. In this paper, we argue that models can have significant gains when spatial structure is preserved in tokenization, and is explicitly used in the mixing stage. We propose two key contributions: (1) Structure-aware Tokenization and, (2) Structure-aware Mixing, both of which can be combined with existing models with minimal effort. We introduce a family of models (SWAT), showing improvements over the likes of DeiT, MLP-Mixer and Swin Transformer, across multiple benchmarks including ImageNet classification and ADE20K segmentation. Our code and models will be released online.
Abstract (translated)
URL
https://arxiv.org/abs/2111.13677
