Unveiling Audio-Visual Learning
Ishan and Tim delve into the intricate interaction between audio and visual data, showcasing how finding similarities between different feature spaces can enhance learning outcomes. Ishan's surprising success with contrastive learning on 3D point clouds challenges traditional notions and opens new possibilities for pre-training in the 3D domain.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Related Questions