Image Representation Learning
Simon explains the concept of negative sampling in image representation learning, emphasizing the importance of keeping views of the same image close and far from other images. The discussion delves into the challenge of mapping representations of similar objects together while keeping representations of dissimilar objects apart in a large batch setting.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!
Related Questions