BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning

arXiv:2404.01179v1 Announce Type: cross
Abstract: Data mixing methods play a crucial role in semi-supervised learning (SSL), but their application is unexplored in long-tailed semi-supervised learning (LTSSL). The primary reason is that the in-batch mixing manner fails to address class imbalance. Furthermore, existing LTSSL methods mainly focus on re-balancing data quantity but ignore class-wise uncertainty, which is also vital for class balance. For instance, some classes with sufficient samples might still exhibit high uncertainty due to indistinguishable features. To this end, …

abstract application arxiv class cs.cv cs.lg data entropy focus reason role semi-supervised semi-supervised learning ssl supervised learning type