DMOFC: Discrimination Metric-Optimized Feature Compression

arXiv:2405.04044v1 Announce Type: new
Abstract: Feature compression, as an important branch of video coding for machines (VCM), has attracted significant attention and exploration. However, the existing methods mainly focus on intra-feature similarity, such as the Mean Squared Error (MSE) between the reconstructed and original features, while neglecting the importance of inter-feature relationships. In this paper, we analyze the inter-feature relationships, focusing on feature discriminability in machine vision and underscoring its significance in feature compression. To maintain the feature discriminability of …

abstract arxiv attention coding compression cs.cv discrimination error exploration feature features focus however importance machines mean paper relationships type video while