Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations

[Free GPT-4]
[PDF] arxiv.org

Improving Pre-Trained Self-Supervised Embeddings Through Effective Entropy Maximization

D Chakraborty, Y LeCun, TGJ Rudner… - ar** embeddings that provide the …
保存 引用 関連記事 全 2 バージョン HTMLバージョン
[Free GPT-4]
[PDF] openreview.net

Harnessing small projectors and multiple views for efficient vision pretraining

A Ghosh, KK Agrawal, S Sodhani, A Oberman… - The Thirty-eighth Annual … - openreview.net
Recent progress in self-supervised (SSL) visual representation learning has led to the
development of several different proposed frameworks that rely on augmentations of images …
保存 引用 関連記事 HTMLバージョン