Framework-agnostic Semantically-aware Global Reasoning for Segmentation

arXiv:2212.03338v2 Announce Type: replace-cross
Abstract: Recent advances in pixel-level tasks (e.g. segmentation) illustrate the benefit of of long-range interactions between aggregated region-based representations that can enhance local features. However, such aggregated representations, often in the form of attention, fail to model the underlying semantics of the scene (e.g. individual objects and, by extension, their interactions). In this work, we address the issue by proposing a component that learns to project image features into latent representations and reason between them using …

abstract advances arxiv attention benefit cs.cv cs.lg extension features form framework global however interactions objects pixel reasoning segmentation semantics tasks type