Diverse Imagenet Models Transfer Better

no code implementations • 19 Apr 2022 • Niv Nayman, Avram Golbert, Asaf Noy, Tan Ping, Lihi Zelnik-Manor

Encouraged by the recent transferability results of self-supervised models, we propose a method that combines self-supervised and supervised pretraining to generate models with both high diversity and high accuracy, and as a result high transferability.

Diversity Multi-Label Classification