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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Multi-Label Classification | MS-COCO 2014 (test) | -- | 81 | |
| Multi-label recognition | MS-COCO | Overall F1 Score (OF1)75.8 | 66 | |
| Multi-label recognition | VG-200 | Avg OF139.9 | 66 | |
| Multi-label recognition | PASCAL VOC 2007 | Avg OF188.2 | 66 | |
| Multi-Label Classification | VOC 07 | mAP90.4 | 61 | |
| Multi-label recognition | PASCAL VOC 2007 (test) | Avg. mAP90.4 | 25 | |
| Multi-label image recognition | VG-200 | Average mAP41.8 | 24 | |
| Multi-label image recognition | PASCAL VOC 2007 | mAP @ 10% Threshold81.5 | 18 | |
| Multi-label image recognition with partial labels | PASCAL VOC 2007 | mAP (IoU=0.10)81.5 | 17 | |
| Multi-label image recognition with partial labels | VG-200 | mAP @ IoU=0.1038.8 | 15 |