A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm

02/26/2020
by   Sungwon Han, et al.
0

Unsupervised embedding learning aims to extract good representation from data without the need for any manual labels, which has been a critical challenge in many supervised learning tasks. This paper proposes a new unsupervised embedding approach, called Super-AND, which extends the current state-of-the-art model. Super-AND has its unique set of losses that can gather similar samples nearby within a low-density space while keeping invariant features intact against data augmentation. Super-AND outperforms all existing approaches and achieves an accuracy of 89.2 for CIFAR-10. We discuss the practical implications of this method in assisting semi-supervised tasks.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset