Self Supervision Insights
Ishan discusses how self-supervision allows models to learn more freely, uncovering the inductive bias already present. Tim questions the role of augmentations in grouping similar images. The conversation delves into the limitations of self-supervised models in associating images with language.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Related Questions