Data Augmentation Debate
Ishan and Tim discuss the potential of removing data augmentations in machine learning training to achieve better representations. They explore the limitations of human-designed augmentations and the idea of learning directly from the real world for improved results in image recognition systems.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Related Questions
What is the main topic of the clip Data vs. Augmentation from the episode Ishan Misra: Self-Supervised Deep Learning in Computer Vision | Lex Fridman Podcast #206?
What is the clip Data vs. Augmentation about from the episode Ishan Misra: Self-Supervised Deep Learning in Computer Vision | Lex Fridman Podcast #206?