Exploring Simple Siamese Representation Learning

Cited by: 0|Bibtex|Views35
Other Links: arxiv.org

Abstract:

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese ...More

Code:

Data:

Your rating :
0

 

Tags
Comments