Title | ||
---|---|---|
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision |
Abstract | ||
---|---|---|
ABSTRACTMulti-label image classification, which can be categorized into label-dependency and region-based methods, is a challenging problem due to the complex underlying object layouts. Although region-based methods are less likely to encounter issues with model generalizability than label-dependency methods, they often generate hundreds of meaningless or noisy proposals with non-discriminative information, and the contextual dependency among the localized regions is often ignored or over-simplified. This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning. Specifically, we propose category-aware weak supervision to concentrate on non-existent categories so as to provide deterministic information for local feature learning, restricting the local branch to focus on more high-quality regions of interest. Moreover, we develop a cross-granularity attention module to explore the complementary information between global and local features, which can build the high-order feature correlation containing not only global-to-local, but also local-to-local relations. Both advantages guarantee a boost in the performance of the whole network. Extensive experiments on two large-scale datasets (MS-COCO and VOC 2007) demonstrate that our framework achieves superior performance over state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1145/3503161.3547834 | International Multimedia Conference |
DocType | ISSN | Citations |
Conference | Zhan J, Liu J, Tang W, et al. Global Meets Local: Effective
Multi-Label Image Classification via Category-Aware Weak
Supervision[C]//Proceedings of the 30th ACM International Conference on
Multimedia. 2022: 6318-6326 | 0 |
PageRank | References | Authors |
0.34 | 0 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiawei Zhan | 1 | 0 | 0.68 |
Jun Liu | 2 | 178 | 25.96 |
Wei Tang | 3 | 0 | 0.34 |
Guannan Jiang | 4 | 0 | 1.01 |
Xi Wang | 5 | 0 | 0.34 |
Bin-Bin Gao | 6 | 0 | 0.68 |
Tianliang Zhang | 7 | 0 | 0.34 |
Wenlong Wu | 8 | 0 | 0.34 |
W. Zhang | 9 | 107 | 45.81 |
Chengjie Wang | 10 | 43 | 19.03 |
Yuan Xie | 11 | 6430 | 407.00 |