SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2208.07576 · ECCV · 2022

Object Discovery via Contrastive Learning for Weakly Supervised Object Detection

Danica Sutherland, Wonho Bae, Daijin Kim, Jinhwan Seo, Junhyug 4⋆

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

Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit from self-supervised instance-level supervision, but since weak supervision does not include count or location information, the most common "argmax" labeling method often ignores many instances of objects. To alleviate this issue, we propose a novel multiple instance labeling method called object discovery. We further introduce a new contrastive loss under weak supervision where no instance-level information is available for sampling, called weakly supervised contrastive loss (WSCL). WSCL aims to construct a credible similarity threshold for object discovery by leveraging consistent features for embedding vectors in the same class. As a result, we achieve new state-of-the-art results on MS-

For agents

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

get_harvested_code_for_paper("2208.07576")
get_code_for_paper("2208.07576")
have("2208.07576")

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

curl https://syntology.ai/api/ran/2208.07576.json

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

[![Syntology run record](https://syntology.ai/api/ran/2208.07576.svg)](https://syntology.ai/paper/2208.07576)

Connect an agent — have() is free.