1 code implementation • 31 Aug 2021 • Vitaliy Kinakh, Olga Taran, Svyatoslav Voloshynovskiy
In this paper, we consider a problem of self-supervised learning for small-scale datasets based on contrastive loss between multiple views of the data, which demonstrates the state-of-the-art performance in classification task.
Ranked #1 on Unsupervised Image Classification on CIFAR-20
no code implementations • 12 Jun 2015 • Sohrab Ferdowsi, Svyatoslav Voloshynovskiy, Dimche Kostadinov
We propose a scheme for multi-layer representation of images.