Deep Common Feature Mining for Efficient Video Semantic Segmentation

arXiv:2403.02689v1 Announce Type: new
Abstract: Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation process, underscore the need for further innovation. In response, we present Deep Common Feature Mining (DCFM), a novel approach strategically designed to address these challenges by leveraging the concept of feature sharing. DCFM explicitly decomposes features into two complementary components. The common representation extracted from a key-frame furnishes …

abstract arxiv challenges computation correlations cs.cv feature innovation mining novel process progress propagation reliability segmentation semantic temporal type video