Evaluating The Robustness of Self-Supervised Representations to Background/Foreground Removal

no code implementations • 2 Jun 2023 • Xavier F. Cadet, Ranya Aloufi, Alain Miranville, Sara Ahmadi-Abhari, Hamed Haddadi

Despite impressive empirical advances of SSL in solving various tasks, the problem of understanding and characterizing SSL representations learned from input data remains relatively under-explored.

Image Classification