2 papers
cs.CV2026
A Self supervised learning framework for imbalanced medical imaging datasets
Yash Kumar Sharma, Charan Ramtej Kodi, Vineet Padmanabhan
Two problems often plague medical imaging analysis: 1) Non-availability of large quantities of labeled training data, and 2) Dealing with imbalanced data, i.e., abundant data are a…
cs.CV2026
Maximally Useful and Minimally Redundant: The Key to Self Supervised Learning for Imbalanced Data
Yash Kumar Sharma, Vineet Padmanabhan
Contrastive self supervised learning(CSSL) usually makes use of the multi-view assumption which states that all relevant information must be shared between all views. The main obje…