Low-Resolution Self-Attention for Semantic Segmentation

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often utilize high-resolution context modeling, resulting in a computational bottleneck. In this work, we challenge conventional wisdom and introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost, i.e., FLOPs. Our approach involves computing self-attention in a fixed low-resolution space, regardless of the input image's resolution, with additional $\text{3}\times \text{3}$3×3 depth-wise convolutions to capture fine details in the high-resolution space. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure. Extensive experiments on the ADE20 K, COCO-Stuff, and CityScapes datasets demonstrate that LRFormer outperforms state-of-the-art models.