Boosting Single Positive Multi-label Classification with Generalized Robust Loss

arXiv:2405.03501v1 Announce Type: new
Abstract: Multi-label learning (MLL) requires comprehensive multi-semantic annotations that is hard to fully obtain, thus often resulting in missing labels scenarios. In this paper, we investigate Single Positive Multi-label Learning (SPML), where each image is associated with merely one positive label. Existing SPML methods only focus on designing losses using mechanisms such as hard pseudo-labeling and robust losses, mostly leading to unacceptable false negatives. To address this issue, we first propose a generalized loss framework based …

abstract annotations arxiv boosting classification cs.ai cs.cv cs.lg focus generalized image labels loss paper positive robust semantic type