OPTiML: Dense Semantic Invariance Using Optimal Transport for Self-Supervised Medical Image Representation

arXiv:2404.11868v1 Announce Type: cross
Abstract: Self-supervised learning (SSL) has emerged as a promising technique for medical image analysis due to its ability to learn without annotations. However, despite the promising potential, conventional SSL methods encounter limitations, including challenges in achieving semantic alignment and capturing subtle details. This leads to suboptimal representations, which fail to accurately capture the underlying anatomical structures and pathological details. In response to these constraints, we introduce a novel SSL framework OPTiML, employing optimal transport (OT), to …

abstract alignment analysis annotations arxiv challenges cs.cv cs.lg however image leads learn limitations medical representation self-supervised learning semantic ssl supervised learning transport type