Abstract
Image classification has witnessed a remarkable advancement in class-balanced benchmarks. However, the natural distribution of datasets in real-world scenarios are long-tailed. Long-tailed classification has become a significant challenge in critical real-world image classification applications. A deep learning network trained on a long-tailed dataset tends to classify tail classes with few samples as head classes with many samples. The severe sample imbalance leads to the overwhelming dominance of negative samples on the tail classes; then, the massive gradient descent of negative samples leads to the classifier’s performance poorly. To tackle this problem, we propose a gradient re-balanced (GREB) loss with two synergistic factors, i.e., balance factor and correction factor. First, GREB estimates the balance and correction factors by accumulating the classifier outputs and their corresponding labels during the training process. Then, GREB dynamically reweights the gradients of positive and negative samples based on the balance factor to minimize the classification bias and improve the classifier performance. Finally, GREB compensates for sample gradients based on the correction factor to minimize the occurrence of misclassifications and improve the precision rate. Experiment results show that our GREB loss achieves state-of-the-art performance on long-tailed multi-label classification datasets (MSCOCO and MultiMNIST) and long-tailed single-label classification datasets (CIFAR10-LT and CIFAR100-LT).
Similar content being viewed by others
Data availability
The datasets generated during and analysed during the current study are available from the corresponding author on reasonable request.
References
Akhbardeh F, Alm CO, Zampieri M, Desell T (2021) Handling extreme class imbalance in technical logbook datasets. Proc Annu Meet Assoc Comput Linguist Int Jt Conf Ntl Lang Process 1:4034–4045
Alafif T, Alzahrani B, Cao Y, Alotaibi R, Barnawi A, Chen M (2022) Generative adversarial network based abnormal behavior detection in massive crowd videos: a hajj case study. J Ambient Intell Humaniz Comput 13(8):4077–4088
Buda M, Maki A, Mazurowski MA (2018) A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw 106:249–259
Cai J, Wang Y, Hwang J-N (2021) Ace: ally complementary experts for solving long-tailed recognition in one-shot. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 112–121
Cao K, Wei C, Gaidon A, Arechiga N, Ma T (2019) Learning imbalanced datasets with label-distribution-aware margin loss. Advances in neural information processing systems. Springer, Cham, p 32
Cao D, Zhu X, Huang X, Guo J, Lei Z (2020). Domain balancing: face recognition on long-tailed domains. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5671–5679
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Chinnappa G, Rajagopal MK (2021) Residual attention network for deep face recognition using micro-expression image analysis. J Ambient Intell Humaniz Comput 1:1–14
Cui Y, Jia M, Lin T-Y, Song Y, Belongie S (2019) Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9268–9277
Dai X (2019) Hybridnet: a fast vehicle detection system for autonomous driving. Signal Process 70:79–88
De Arriba López V, Cobos-Guzman S (2022) Development of a deep learning model for recognising traffic sings focused on difficult cases. J Ambient Intell Humaniz Comput 13(9):4175–4187
Deng Z, Liu H, Wang Y, Wang C, Yu Z, Sun X (2021). Pml: Progressive margin loss for long-tailed age classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 10503–10512
Devunooru S, Alsadoon A, Chandana P, Beg A (2021) Deep learning neural networks for medical image segmentation of brain tumours for diagnosis: a recent review and taxonomy. J Ambient Intell Humaniz Comput 12(1):455–483
Ding R, Guo K, Zhu X, Wu Z, Wang L (2022) ComGAN: unsupervised disentanglement and segmentation via image composition. In: Oh AH, Agarwal A, Belgrave D, Cho K (eds) Advances in neural information processing systems. Springer, Cham
Duarte K, Rawat Y, Shah M (2021) Plm: Partial label masking for imbalanced multi-label classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2739–2748
Gidaris S, Singh P, Komodakis N (2018) Unsupervised representation learning by predicting image rotations. arXiv:1803.07728
Gu C, Sun C, Ross D. A, Vondrick C, Pantofaru C, Li Y, Vijayanarasimhan S, Toderici G, Ricco S, Sukthankar R, et al. (2018) Ava: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 6047–6056
Halim Z, Sulaiman M, Waqas M, Aydın D (2022) Deep neural network-based identification of driving risk utilizing driver dependent vehicle driving features: a scheme for critical infrastructure protection. J Ambient Intell Humaniz Comput 1:1–19
He K, Zhang X, Ren S, Sun J (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 770–778
Hsieh T-I, Robb E, Chen H-T, Huang J-B (2021) Droploss for long-tail instance segmentation. AAAI 3:15
Huang C, Li Y, Loy CC, Tang X (2016) Learning deep representation for imbalanced classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5375–5384
Jamal M. A, Brown M, Yang M-H, Wang L, Gong B (2020). Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 7610–7619
Jing X-Y, Zhang X, Zhu X, Wu F, You X, Gao Y, Shan S, Yang J-Y (2021) Multiset feature learning for highly imbalanced data classification. IEEE Trans Pattern Anal Mach Intell 43:139–156
Kang B, Xie S, Rohrbach M, Yan Z, Gordo A, Feng J, Kalantidis Y (2020) Decoupling representation and classifier for long-tailed recognition
Korycki Ł, Krawczyk B (2021). Concept drift detection from multi-class imbalanced data streams. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), IEEE, pp 1068–1079
Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Technical Report
Kumar Y, Koul A, Singla R, Ijaz MF (2022) Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. J Ambient Intell Humaniz Comput 1:1–28
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp 2278–2324
Li Y Wang T, Kang B, Tang S, Wang C, Li J, Feng J (2020a) Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 10991–11000
Li T, Cao P, Yuan Y, Fan L, Yang Y, Feris R, Indyk P, Katabi D (2021b) Targeted supervised contrastive learning for long-tailed recognition. arXiv:2111.13998
Li S, Gong K, Liu C H, Wang Y, Qiao F, Cheng X (2021c). Metasaug: Meta semantic augmentation for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5212–5221
Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: common objects in context. Computer vision - ECCV 2014. Springer, Cham, pp 740–755
Lin T-Y, Goyal P, Girshick R, He K, Dollár P (2017). Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2980–2988
Liu Z, Miao Z, Zhan X, Wang J, Gong B, Yu S. X (2019). Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2537–2546
Ren J, Zhang M, Yu C, Liu Z (2022) Balanced mse for imbalanced visual regression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7926–7935
Tan J, Wang C, Li B, Li Q, Ouyang W, Yin C,Yan J (2020). Equalization loss for long-tailed object recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 11662–11671
Tan J, Lu X, Zhang G, Yin C, Li Q (2021). Equalization loss v2: A new gradient balance approach for long-tailed object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 1685–1694
Tian J, Chen S, Zhang X, Feng Z, Xiong D, Wu S, Dou C (2021) Re-embedding difficult samples via mutual information constrained semantically oversampling for imbalanced text classification. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp 3148–3161
Wang Y-X, Ramanan D, Hebert M (2017) Learning to model the tail. In: Ch M (ed) Advances in neural information processing systems. Springer, Cham, p 30
Wang J, Lukasiewicz T, Hu X, Cai J, Xu Z (2021a) Rsg: A simple but effective module for learning imbalanced datasets. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 3784–3793
Wang J, Zhang W, Zang Y, Cao Y, Pang J, Gong T, Chen, K, Liu Z, Loy C C, Lin D (2021b) Seesaw loss for long-tailed instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9695–9704
Wang P, Han K, Wei, X.-S, Zhang L, Wang L (2021c) Contrastive learning based hybrid networks for long-tailed image classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 943–952
Wang X, Lian L, Miao Z, Liu Z, Yu S (2021e) Long-tailed recognition by routing diverse distribution-aware experts. arXiv:2010.01809
Wang T, Zhu Y, Zhao C, Zeng W, Wang J, Tang M (2021d). Adaptive class suppression loss for long-tail object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 3103–3112
Yu S, Guo J, Zhang R, Fan Y, Wang Z, Cheng X (2022). A re-balancing strategy for class-imbalanced classification based on instance difficulty. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 70–79
Zhou B, Cui Q, Wei X.-S, Chen Z.-M (2020). Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9719–9728
Zhu X, Guo K, Fang H, Chen L, Ren S, Hu B (2022a) Cross view capture for stereo image super-resolution. IEEE Trans Multimed 24:3074–3086
Zhu X, Guo K, Ren S, Hu B, Hu M, Fang H (2022b) Lightweight image super-resolution with expectation-maximization attention mechanism. IEEE Trans Circuits Syst Video Technol 32(3):1273–1284
Acknowledgements
This work was supported in part by the Natural Science Foundation of China under Grant 62076255; in part by the Open Research Projects of Zhejiang Lab (NO. 2022RC0AB07); in part by the Hunan Provincial Science and Technology Plan Project 2020SK2059; in part by the Key projects of Hunan Education Department 20A88; in part by the National Science Foundation of Hunan Province 2021JJ30082; in part by the Yongzhou City Instructive Science and Technology Plan Project 2021YZKJZD003; in part by the Scientific Research Projects of Hunan University of Science and Engineering 20XKY054.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest in this work. The authors have employed some public datasets, namely, MSCOCO, MNIST, CIFAR10, CIFAR100 for performing the experiments in the considered work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wu, Z., Guo, K., Ren, S. et al. GREB: gradient re-balanced loss for long-tailed multi-lable classification. J Ambient Intell Human Comput 14, 7937–7948 (2023). https://doi.org/10.1007/s12652-023-04602-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-023-04602-z