SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13223 · CVPR · 2023

Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels

Qiang Zhang, Jungong Han, Hui Chen, Ao Wang, Pengzhang Liu, Yongjun Bao, Weipeng Yan, Zixuan Ding

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

Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the imageto-label correspondence in the vision-language model, i.e., CLIP [22], to compensate for insufficient annotations. In spite of promising performance, they generally overlook the valuable prior about the label-to-label correspondence. In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter. We then present a novel Semantic Correspondence Prompt Network (SCP-Net), which can thoroughly explore the structured semantic prior. A Prior-Enhanced Self-Supervised Learning method is further introduced to enhance the use of the prior. Comprehensive experiments and analyses on several widely used benchmark datasets show that our method significantly outperforms existing methods on all datasets, well demonstrating the effectiveness and the superiority of our method. Our code will be available at https://github.com/ jameslahm/SCPNet.

For agents

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

get_harvested_code_for_paper("2303.13223")
get_code_for_paper("2303.13223")
have("2303.13223")

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

curl https://syntology.ai/api/ran/2303.13223.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.13223.svg)](https://syntology.ai/paper/2303.13223)

Connect an agent — have() is free.