English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present a new method of self-supervised learning and knowledgedistillation based on the multi-views and multi-representations (MV-MR). TheMV-MR is based on the maximization of dependence between learnable embeddingsfrom augmented and non-augmented views, jointly with the maximization ofdependence between learnable embeddings from augmented view and multiplenon-learnable representations from non-augmented view. We show that theproposed method can be used for efficient self-supervised classification andmodel-agnostic knowledge distillation. Unlike other self-supervised techniques,our approach does not use any contrastive learning, clustering, or stopgradients. MV-MR is a generic framework allowing the incorporation ofconstraints on the learnable embeddings via the usage of imagemulti-representations as regularizers. Along this line, knowledge distillationis considered a particular case of such a regularization. MV-MR provides thestate-of-the-art performance on the STL10 and ImageNet-1K datasets amongnon-contrastive and clustering-free methods. We show that a lower complexityResNet50 model pretrained using proposed knowledge distillation based on theCLIP ViT model achieves state-of-the-art performance on STL10 linearevaluation. The code is available at: https://github.com/vkinakh/mv-mr

MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation