Optimizing Contrastive Learning with Semi-Online Triplet Mining
Source abstract
Abstract
Contrastive learning is a machine learning technique in which models learn by contrasting similar and dissimilar data points. Its goal is to learn a representation of data in such a way that similar instances are close together in the representation space, while dissimilar instances are far apart. Our industrial use case focuses on a special case of contrastive learning called triplet learning. Building triplets with adequate difficulty is crucial to effective training convergence in such a setup. By combining online and offline mining techniques, we propose a method of mining hard triplets that is both performant and memory-inexpensive. Our experiments demonstrate that the method leads to improved identity pairing (which is the specific case of clustering) both on a real-life industry shoe dataset and on a generated benchmark one.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Face and Expression Recognition · Machine Learning and ELM
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Information Processing Institute, 00-608 Warsaw, Poland
Vive Textile Recycling, 25-663 Kielce, Poland
References (31)
Show source-provided references
1. Schroff, F., Kalenichenko, D., and Philbin, J. (2015, January 7–12). FaceNet: A Unified Embedding for Face Recognition and Clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298682 ↗
2. Kozłowski, M., Buczkowski, P., and Brzeziński, P. (2022). Novel Process of Shoe Pairing Using Computer Vision and Deep Learning Methods. Digital Interaction and Machine Intelligence, Springer.10.1007/978-3-031-37649-8_4 ↗
3. Faghih, E., Saki, Z., and Moore, M. (2025). A Systematic Literature Review—AI-Enabled Textile Waste Sorting. Sustainability, 17.10.3390/su17104264 ↗
4. Qualitative classification of waste textiles based on near infrared spectroscopy and the convolutional network10.1177/0040517519886032 ↗
5. Cura, K., Rintala, N., Kamppuri, T., Saarimäki, E., and Heikkilä, P. (2021). Textile recognition and sorting for recycling at an automated line using near infrared spectroscopy. Recycling, 6.10.3390/recycling6010011 ↗
6. Qualitative identification of waste textiles based on near-infrared spectroscopy and the back propagation artificial neural network10.1177/00405175211007516 ↗
7. Recycled clothing classification system using intelligent IoT and deep learning with AlexNet10.1155/2021/5544784 ↗
8. Furferi, R., and Servi, M. (2023). A machine vision-based algorithm for color classification of recycled wool fabrics. Appl. Sci., 13.10.3390/app13042464 ↗
9. Bhoomika, and Verma, G. (2024, January 15–16). Optimizing EfficientNetB0 for Shoe Brand Identification: A Comparative Analysis. Proceedings of the 2024 Second International Conference Computational and Characterization Techniques in Engineering & Sciences (IC3TES), Lucknow, India.10.1109/IC3TES62412.2024.10877438 ↗
10. Gill, K.S., Sharma, A., Anand, V., and Gupta, R. (2023, January 5–6). Smart Shoe Classification Using Artificial Intelligence on EfficientnetB3 Model. Proceedings of the 2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT), Gharuan, India.10.1109/InCACCT57535.2023.10141787 ↗
11. Backpropagation Applied to Handwritten Zip Code Recognition10.1162/neco.1989.1.4.541 ↗
12. Convolutional networks for images, speech, and time series
13. Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18–24). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning, Virtual Event.
14. Huang, G., Liu, Z., Van der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
15. Tan, M., and Le, Q.V. (2019, January 9–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
16. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
17. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
18. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.
19. Lin, M., Chen, Q., and Yan, S. (2014, January 14–16). Network In Network. Proceedings of the International Conference on Learning Representations, Banff, AB, Canada.
20. Reminder of the First Paper on Transfer Learning in Neural Networks, 197610.31449/inf.v44i3.2828 ↗
21. Hermans, J.R., Spanakis, G., and Möckel, R. (2017, January 9). Accumulated Gradient Normalization: A Robust Optimization Technique for Distributed Asynchronous Training. Proceedings of the First Workshop on Optimization for Machine Learning (OPT 2017), Long Beach, CA, USA.
22. Solution of a Large-Scale Traveling-Salesman Problem
23. Visualizing Data using t-SNE
24. McInnes, L., Healy, J., and Melville, J. (2018). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv.10.21105/joss.00861 ↗
25. Johnson, S.C. (1967). Hierarchical Clustering Schemes. Psychometrika, Springer.10.1007/BF02289588 ↗
26. Depth-First Search and Linear Graph Algorithms10.1137/0201010 ↗
27. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
28. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the Difficulty of Training Deep Feedforward Neural Networks. Proceedings of the International Conference on Artificial Intelligence and Statistics 2010, Sardinia, Italy.
29. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv.
30. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016). TensorFlow: A system for large-scale machine learning. arXiv.
31. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.