International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Triplet Class-Wise Difficulty-Based Loss for Long Tail Classification

  • Yaw Darkwah Jnr. (Department of Computer Engineering, Dongseo University) ;
  • Dae-Ki Kang (Department of Computer Engineering, Dongseo University)
  • Received : 2023.05.23
  • Accepted : 2023.06.02
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Little attention appears to have been paid to the relevance of learning a good representation function in solving long tail tasks. Therefore, we propose a new loss function to ensure a good representation is learnt while learning to classify. We call this loss function Triplet Class-Wise Difficulty-Based (TriCDB-CE) Loss. It is a combination of the Triplet Loss and Class-wise Difficulty-Based Cross-Entropy (CDB-CE) Loss. We prove its effectiveness empirically by performing experiments on three benchmark datasets. We find improvement in accuracy after comparing with some baseline methods. For instance, in the CIFAR-10-LT, 7 percentage points (pp) increase relative to the CDB-CE Loss was recorded. There is more room for improvement on Places-LT.

Keywords

Acknowledgement

This work was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (NRF-2022R1A2C2012243) in 2023.

References

  1. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "ImageNet: A large-scale hierarchical image database," in 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL: IEEE, Jun., pp. 248-255.
  2. S. Sinha, H. Ohashi, and K. Nakamura, "Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance," in Proceedings of the Asian Conference on Computer Vision, Springer International Publishing, 2020, pp. 549-565.
  3. X. Zhang, Z. Fang, Y. Wen, Z. Li, and Y. Qiao, "Range Loss for Deep Face Recognition with Long-Tailed Training Data," in 2017 IEEE International Conference on Computer Vision (ICCV), Venice: IEEE, Oct., pp. 5419-5428.
  4. C. Wei, K. Sohn, C. Mellina, A. Yuille, and F. Yang, "CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning," in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA: IEEE, Jun. 2021, pp. 10852-10861.
  5. E. Hoffer and N. Ailon, "Deep Metric Learning Using Triplet Network," in Similarity-Based Pattern Recognition, A. Feragen, M. Pelillo, and M. Loog, Eds., in Lecture Notes in Computer Science, Vol. 9370. Cham: Springer International Publishing, 2015, pp. 84-92.
  6. Z. Liu, Z. Miao, X. Zhan, J. Wang, B. Gong, and S. X. Yu, "Large-Scale Long-Tailed Recognition in an Open World," in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2019.
  7. X.-Y. Liu, J. Wu, and Z.-H. Zhou, "Exploratory Undersampling for Class-Imbalance Learning," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 39, No. 2, pp. 539-550, Apr. 2009. https://doi.org/10.1109/TSMCB.2008.2007853
  8. K. E. Bennin, J. Keung, P. Phannachitta, A. Monden, and S. Mensah, "MAHAKIL: Diversity Based Oversampling Approach to Alleviate the Class Imbalance Issue in Software Defect Prediction," IEEE Transactions on Software Engineering, Vol. 44, No. 6, pp. 534-550, Jun. 2018. https://doi.org/10.1109/TSE.2017.2731766
  9. B. Kang et al., "Decoupling Representation and Classifier for Long-Tailed Recognition," in 8th International Conference on Learning Representations, 2020.
  10. Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie, "Class-Balanced Loss Based on Effective Number of Samples," in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA: IEEE, Jun. 2019, pp. 9260-9269.
  11. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, "Focal Loss for Dense Object Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 42, No. 2, pp. 318-327, Feb. 2020. https://doi.org/10.1109/TPAMI.2018.2858826
  12. M. A. Jamal, M. Brown, M.-H. Yang, L. Wang, and B. Gong, "Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2020.
  13. X. Yin, X. Yu, K. Sohn, X. Liu, and M. Chandraker, "Feature Transfer Learning for Face Recognition With Under-Represented Data," in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2019.
  14. A. Sahoo, A. Singh, R. Panda, R. Feris, and A. Das, "Mitigating Dataset Imbalance via Joint Generation and Classification," in Computer Vision - ECCV 2020 Workshops, Springer International Publishing, 2020, pp. 177-193.
  15. L. Xiang, G. Ding, and J. Han, "Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification," in Computer Vision - ECCV 2020, A. Vedaldi, H. Bischof, T. Brox, and J.-M. Frahm, Eds., in Lecture Notes in Computer Science, Vol. 12350. Cham: Springer International Publishing, 2020, pp. 247-263.
  16. G. Mariani, F. Scheidegger, R. Istrate, C. Bekas, and C. Malossi, "BAGAN: Data Augmentation with Balancing GAN," 2018, arXiv:1803.09655.
  17. A. Krizhevsky and G. Hinton, "Learning multiple layers of features from tiny images," University of Toronto, Toronto, Ontario, Technical Report, 2009.
  18. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA: IEEE, Jun. 2016, pp. 770-778.
  19. B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba, "Places: A 10 million Image Database for Scene Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017.
  20. T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, "Distributed Representations of Words and Phrases and their Compositionality," in Advances in Neural Information Processing Systems, C. J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, Eds., Curran Associates, Inc., 2013.
  21. K. Cao, C. Wei, A. Gaidon, N. Arechiga, and T. Ma, "Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss," in Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alche-Buc, E. Fox, and R. Garnett, Eds., Curran Associates, Inc., 2019.
  22. S. Gidaris and N. Komodakis, "Dynamic Few-Shot Visual Learning Without Forgetting," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, Jun. 2018, pp. 4367-4375.