Self-Supervised Learning Insights
Ishan shares how using random images for self-supervised learning testing revealed the impact of human inductive bias. Quality of data plays a crucial role in representation quality, showing the importance of curating data similar to ImageNet for better performance.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Related Questions