Hyeonho Song, Hard Negative Mixing for Contrastive Learning
https://kaist.zoom.us/j/98984764325Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images apart, one can train highly transferable visual representations. As revealed by recent studies, heavy data augmentation and large …