ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification

arXiv:2401.01448v2 Announce Type: replace-cross
Abstract: Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture label dependencies. However, these methods often include complex modules that entail heavy computation and lack interpretability. In this paper, we propose Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address these challenges in multi-label image classification tasks. Our simple yet effective approach employs supervised contrastive …

abstract arxiv classification computation computer computer vision cs.cv cs.lg dependencies domains graph graph-based however image imaging interpretability medical medical imaging modules performance simple transformer type vision visual