Skip to content

Dense Contrastive Learning for Self Supervised Visual Pre Training

Properties
authors Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li
year 2021
url http://arxiv.org/abs/2011.09157

Abstract

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning (DenseCL), which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images.

Notes

Zotero Link

Pasted image 20250310213431.png

Pasted image 20250310213443.png