Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks . However, embedding clustering limits its extension to the extremely large-scale dataset due to its prerequisite to save the global latent embedding of the entire dataset… In this work, we aim to make this framework more simple and elegant without performance decline . Extensive experiments on ImageNet dataset have been conducted to prove the effectiveness of our method . Furthermore, the experiments on transfer learning benchmarks have verified its generalization to other downstream tasks, including multi-label image classification, object detection, semantic segmentation and few-shot image classification . For detailed interpretation, we further analyze its relation with

Links: PDF - Abstract

Code :

None

Keywords : learning - dataset - image - classification - experiments -

Leave a Reply

Your email address will not be published. Required fields are marked *