The paper focuses on improving the performance of multi-label image classification by enhancing the convergence of the triplet loss function with a flexible margin. To achieve this, several modifications to the loss function itself and the training process were analyzed, aiming to stabilize gradient descent and reach the loss function minimum more efficiently. Based on the analysis, several promising hypotheses were identified for experimental evaluation: adopting the distance computation approach from the focal loss, replacing the linear increase of the margin parameter with a logarithmic one, balancing classes within a batch, and adjusting batch size. The proposed convergence improvement methods were tested on the open-source CIFAR dataset with hierarchical labels. The effectiveness of the selected methods was confirmed: each modification increased the final model accuracy by 2–4%, while applying all of them together improved classification accuracy by 10% for lower-level labels and 12% for higher-level labels. The proposed methods were also evaluated for robustness to dataset noise. It was shown that the convergence improvement method based on batch class balancing is sensitive to data errors and is therefore not recommended for use with noisy datasets.
1. Petrova I.S. Method of Training Image Classifiers Using Additional Labels. Modeling, Optimization and Information Technology. 2025;13(2). (In Russ.). https://doi.org/10.26102/2310-6018/2025.49.2.041
2. Deng W., Zhang J., Zhang P., Yao Y., Gao H., Zhang Y. Hyper-Label-Graph: Modeling Branch-Level Dependencies of Labels for Hierarchical Multi-Label Text Classification. In: ACML 2023: Asian Conference on Machine Learning, 11–14 November 2023, Istanbul, Turkey. PMLR; 2023. P. 279–294.
3. Suloev K.K., Sheshkus A.V., Arlazarov V.L. Spherical Constraints in the Triplet Loss Function. Proceedings of the Institute for Systems Analysis Russian Academy of Sciences. 2023;73(2):50–58. (In Russ.). https://doi.org/10.14357/20790279230205
4. Zhang Sh., Zhang Q., Wei X., Zhang Y., Xia Y. Person Re-Identification with Triplet Focal Loss. IEEE Access. 2018;6:78092–78099. https://doi.org/10.1109/ACCESS.2018.2884743
5. Xuan H., Stylianou A., Pless R. Improved Embeddings with Easy Positive Triplet Mining. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 01–05 March 2020, Snowmass, CO, USA. IEEE; 2020. P. 2463–2471. https://doi.org/10.1109/WACV45572.2020.9093432
6. Suyal H., Shivhare Sh.N., Shrivastava G., Singh R., Singhal A. IA-KNNR: A Novel Imbalance-Aware Approach for Handling Multi-Label Class Imbalance Problem. IEEE Access. 2025;13:119999–120017. https://doi.org/10.1109/ACCESS.2025.3586146
7. Liu W., Wang H., Shen X., Tsang I.W. The Emerging Trends of Multi-Label Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021;44(11):7955–7974. https://doi.org/10.1109/TPAMI.2021.3119334
8. Sumbul G., Ravanbakhsh M., Demir B. Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval. IEEE Transactions on Geoscience and Remote Sensing. 2021;60. https://doi.org/10.1109/TGRS.2021.3124326
9. Wang Ch., Liu F., Chen Y., Frazer H., Carneiro G. Cross- and Intra-Image Prototypical Learning for Multi-Label Disease Diagnosis and Interpretation. IEEE Transactions on Medical Imaging. 2025;44(6):2568–2580. https://doi.org/10.1109/TMI.2025.3541830
10. Wang X., Han X., Huang W., Dong D., Scott M.R. Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 15–20 June 2019, Long Beach, CA, USA. IEEE; 2019. P. 5017–5025. https://doi.org/10.1109/CVPR.2019.00516
11. Shao R., Xu N., Geng X. Multi-Label Learning with Label Enhancement. In: 2018 IEEE International Conference on Data Mining (ICDM), 17–20 November 2018, Singapore. IEEE; 2018. P. 437–446. https://doi.org/10.1109/ICDM.2018.00059
12. Kharbanda S., Gupta D., K G., et al. UniDEC: Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification. In: WWW '25: Proceedings of the ACM on Web Conference 2025, 28 April – 02 May 2025, Sydney, Australia. New York: Association for Computing Machinery; 2025. P. 4124–4133. https://doi.org/10.1145/3696410.37147
13. Csányi G.M., Vági R., Megyeri A., et al. Can Triplet Loss Be Used for Multi-Label Few-Shot Classification? A Case Study. Information. 2023;14(10). https://doi.org/10.3390/info14100520
14. Kalra D.S., Barkeshli M. Why Warmup the Learning Rate? Underlying Mechanisms and Improvements. In: NeurIPS 2024: Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 10–15 December 2024, Vancouver, BC, Canada. 2024. P. 111760–111801. https://doi.org/10.52202/079017-3549
