Data Hunger in Self-Supervised Learning
Ishan and others discuss the data hunger of self-supervised models, emphasizing the need for vast amounts of data for effective learning. They delve into the challenges of current modeling techniques and the limitations of augmentations in training these models efficiently.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Related Questions