SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.09775 · CVPR · 2022

ContrastMask: Contrastive Learning to Segment Every Thing

Yan Wang, Wei Shen, Shouhong Ding, Xuehui Wang, Kai Zhao, Ruixin Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

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

Abstract

Partially-supervised instance segmentation is a task which requests segmenting objects from novel categories via learning on limited base categories with annotated masks thus eliminating demands of heavy annotation burden. The key to addressing this task is to build an effective classagnostic mask segmentation model. Unlike previous methods that learn such models only on base categories, in this paper, we propose a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework. In this framework, annotated masks of base categories and pseudo masks of novel categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa. Through this framework, feature discrimination between foreground and background is largely improved, facilitating learning of the class-agnostic mask segmentation model. Exhaustive experiments on the COCO dataset demonstrate the superiority of our method, which outperforms previous state-of-the-arts.

For agents

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

get_harvested_code_for_paper("2203.09775")
get_code_for_paper("2203.09775")
have("2203.09775")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.09775.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.09775.svg)](https://syntology.ai/paper/2203.09775)

Connect an agent — have() is free.