EUVIMEDEUVIMED entdecken
Crossref

Multi-Label Image Classification via Contrastive Co-Occurrence Learning

Xuelin Zhu, Jian Liu, Dongqi Tang, Weijia Liu, Jiawei Ge, Bo Liu, Jiuxin Cao

IEEE Transactions on Image Processing · 2026 · 35 · 6700-6713

DOI: 10.1109/tip.2026.3700934 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Xuelin Zhu und 6 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Jiangsu Provincial Key Laboratory of Computer Networking Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-label image classification is an essential task in computer vision that aims to identify multiple objects in images. Recently, there has been growing research interest in modeling the relationships between labels to enhance label representation learning. An intuitive approach is to train a network to estimate label co-occurrence probabilities in a supervised manner, which are then leveraged to guide the interactions between label representations. However, the extreme sparsity of label co-occurrence signals poses substantial challenges. To address this issue, we commence by examining the potential interaction behaviors between label representations under the guidance of ground-truth label co-occurrence signals. Inspired by our findings, a novel contrastive learning mechanism is crafted to mimic and enhance such behaviors, facilitating effective label representation interactions without relying on explicit supervision from label co-occurrence signals. Based on this, we develop a pioneering contrastive co-occurrence learning framework, which operates on the instance-level label co-occurrence graph for multi-label image classification. This framework involves sequential processes of label representation learning followed by co-occurrence perception learning. Cross-entropy loss for label classification learning and contrastive loss for co-occurrence perception learning are used to jointly optimize the entire framework end-to-end. In this way, label representations can interact effectively, fully perceiving their co-occurrence relationships at the instance level, thereby significantly improving the performance in label recognition. Extensive experiments on public benchmarks demonstrate the superiority of the proposed framework in multi-label image classification. Codes are available on https://github.com/jasonseu/CoCo.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • Jiangsu Provincial Key Laboratory of Computer Networking Technology
  • Jiangsu Provincial Key Laboratory of Network and Information Security
  • Key Laboratory of Computer Network and Information Integration of Ministry of Education of China
  • Nanjing Purple Mountain Laboratories

Zitieren

APA

Zhu, X., Liu, J., Tang, D., Liu, W., Ge, J., Liu, B., & Cao, J. (2026). Multi-Label Image Classification via Contrastive Co-Occurrence Learning. IEEE Transactions on Image Processing, 35, 6700-6713. https://doi.org/10.1109/tip.2026.3700934

Vancouver

Zhu X, Liu J, Tang D, Liu W, Ge J, Liu B, et al. Multi-Label Image Classification via Contrastive Co-Occurrence Learning. IEEE Transactions on Image Processing. 2026;35:6700-6713. doi:10.1109/tip.2026.3700934

BibTeX
@article{Zhu2026,
  author = {Zhu, Xuelin and Liu, Jian and Tang, Dongqi and Liu, Weijia and Ge, Jiawei and Liu, Bo and Cao, Jiuxin},
  title = {Multi-Label Image Classification via Contrastive Co-Occurrence Learning},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {6700--6713},
  doi = {10.1109/tip.2026.3700934}
}
Kostenlos starten →