Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Structured Semantic Transfer for Multi-Label Recognition with Partial Labels

About

Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both the input images and output label spaces. To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i.e., merely some labels are known while other labels are missing (also called unknown labels) per image. The framework consists of two complementary transfer modules that explore within-image and cross-image semantic correlations to transfer knowledge of known labels to generate pseudo labels for unknown labels. Specifically, an intra-image semantic transfer module learns image-specific label co-occurrence matrix and maps the known labels to complement unknown labels based on this matrix. Meanwhile, a cross-image transfer module learns category-specific feature similarities and helps complement unknown labels with high similarities. Finally, both known and generated labels are used to train the multi-label recognition models. Extensive experiments on the Microsoft COCO, Visual Genome and Pascal VOC datasets show that the proposed SST framework obtains superior performance over current state-of-the-art algorithms. Codes are available at https://github.com/HCPLab-SYSU/HCP-MLR-PL.

Tianshui Chen, Tao Pu, Hefeng Wu, Yuan Xie, Liang Lin• 2021

Related benchmarks

TaskDatasetResultRank
Multi-Label ClassificationMS-COCO 2014 (test)--
81
Multi-label recognitionMS-COCO
Overall F1 Score (OF1)75.8
66
Multi-label recognitionVG-200
Avg OF139.9
66
Multi-label recognitionPASCAL VOC 2007
Avg OF188.2
66
Multi-Label ClassificationVOC 07
mAP90.4
61
Multi-label recognitionPASCAL VOC 2007 (test)
Avg. mAP90.4
25
Multi-label image recognitionVG-200
Average mAP41.8
24
Multi-label image recognitionPASCAL VOC 2007
mAP @ 10% Threshold81.5
18
Multi-label image recognition with partial labelsPASCAL VOC 2007
mAP (IoU=0.10)81.5
17
Multi-label image recognition with partial labelsVG-200
mAP @ IoU=0.1038.8
15
Showing 10 of 14 rows

Other info

Code

Follow for update