ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images

Junzhou Huang, Lei He, Jianhua Yao, Liang, Jiawei Yang, Hanbo Chen, Yuan ⋆⋆

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• TencentAILabHealthcare/ConCL

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Detecting and segmenting objects within whole slide images is essential in computational pathology workflow. Self-supervised learning (SSL) is appealing to such annotation-heavy tasks. Despite the extensive benchmarks in natural images for dense tasks, such studies are, unfortunately, absent in current works for pathology. Our paper intends to narrow this gap. We first benchmark representative SSL methods for dense prediction tasks in pathology images. Then, we propose concept contrastive learning (ConCL), an SSL framework for dense pre-training. We explore how ConCL performs with concepts provided by different sources and end up with proposing a simple dependencyfree concept generating method that does not rely on external segmentation algorithms or saliency detection models. Extensive experiments demonstrate the superiority of ConCL over previous state-of-the-art SSL methods across different settings. Along our exploration, we distill several important and intriguing components contributing to the success of dense pre-training for pathology images. We hope this work could provide useful data points and encourage the community to conduct ConCL pre-training for problems of interest. Code is available at https: //github.com/TencentAILabHealthcare/ConCL.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.06733")
get_code_for_paper("2207.06733")
have("2207.06733")

Connect an agent — have() is free.