Multi-Scale Representations by Varying Window Attention for Semantic Segmentation

arXiv:2404.16573v1 Announce Type: new
Abstract: Multi-scale learning is central to semantic segmentation. We visualize the effective receptive field (ERF) of canonical multi-scale representations and point out two risks in learning them: scale inadequacy and field inactivation. A novel multi-scale learner, varying window attention (VWA), is presented to address these issues. VWA leverages the local window attention (LWA) and disentangles LWA into the query window and context window, allowing the context's scale to vary for the query to learn representations at …

abstract arxiv attention canonical cs.cv novel risks scale segmentation semantic them type