Self-Supervised Representation Learning with Meta Comprehensive Regularization

arXiv:2403.01549v1 Announce Type: new
Abstract: Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the shared information among multiple augmented views of samples, while disregarding the non-shared information that may be beneficial for downstream tasks. To address this issue, we introduce a module called CompMod with Meta Comprehensive Regularization (MCR), embedded into existing self-supervised frameworks, to make the learned …

abstract arxiv augmentation concept cs.cv data harness information meta multiple regularization representation representation learning samples self-supervised learning semantic ssl strategies supervised learning type