Dataset

Metrics

Survey

Balancing

• I Malkiel, L Wolf, "Mtadam: Automatic balancing of multiple training loss terms", arXiv preprint arXiv:2006.14683, 2020.

Object Detection

Classification

• [Focal Loss] Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollar. "Focal loss for dense object detection". In ´ Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.

• [QFL] X. Li, W. Wang, L. Wu, S. Chen, X. Hu, J. Li, J. Tang, and J. Yang. "Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection". Advances in Neural Information Processing Systems, 33:21002–21012, 2020.

• [VFL] Haoyang Zhang, Ying Wang, Feras Dayoub, and Niko Sunderhauf. "Varifocalnet: An iou-aware dense object detector". In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8514–8523, 2021. 

• [Poly]  Zhaoqi Leng, Mingxing Tan, Chenxi Liu, Ekin Dogus Cubuk, Xiaojie Shi, Shuyang Cheng, and Dragomir Anguelov. "Polyloss: A polynomial expansion perspective of classification loss functions". arXiv preprint arXiv:2204.12511, 2022.

Box Regression

• [IoU Loss] Jiahui Yu, Yuning Jiang, Zhangyang Wang, Zhimin Cao, and Thomas Huang. Unitbox: An advanced object detection network. In Proceedings of the 24th ACM international conference on Multimedia, pages 516–520, 2016. 

• [GIoU] Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, and Silvio Savarese. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 658–666, 2019.

• [DIoU] [CIoU] Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, and Dongwei Ren. Distance-iou loss: Faster and better learning for bounding box regression. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 12993–13000, 2020. 

• [α-IoU] Jiabo He, Sarah Erfani, Xingjun Ma, James Bailey, Ying Chi, and Xian-Sheng Hua. α-iou: A family of power intersection over union losses for bounding box regression. Advances in Neural Information Processing Systems, 34:20230–20242, 2021.

• [SIoU] Zhora Gevorgyan. Siou loss: More powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740, 2022.

• [DFL] Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Advances in Neural Information Processing Systems, 33:21002–21012, 2020.

• [DFLv2] Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang. Generalized focal loss v2: Learning reliable localization quality estimation for dense object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11632–11641, 2021.

Semantic Segmentation

Distribution-based Loss

• [CE] M. Yi-de, L. Qing, Q. Zhi-Bai, "Automated Image Segmentation using Improved PCNN Model based on Cross-entropy", Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. (Cross Entropy)

• [BCE]

• [WCE] Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015. (Weighted Cross-Entropy)

• [Balanced CE] 

• [TopK] Wu, Zifeng, Chunhua Shen, and Anton van den Hengel. "Bridging category-level and instance-level semantic image segmentation." arXiv preprint arXiv:1605.06885 (2016).

• [Focal Loss] T. Lin, P. Goyal, R. Girshick, K. He and P. Dollár, "Focal Loss for Dense Object Detection," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 2999-3007. 

• [DPCE] Caliva, F., Iriondo, C., Martinez, A. M., Majumdar, S., and Pedoia, V. "Distance Map Loss Penalty Term for Semantic Segmentation." MILD Abstract (2019). (Distance Map Drived Loss Penalty term)

Region-based Loss

• [SS] Brosch T., Yoo Y., Tang L.Y.W., Li D.K.B., Traboulsee A., Tam R. "Deep convolutional encoder networks for multiple sclerosis lesion segmentation." International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2015. (Sensitivity-Specificity (SS) loss)

• [DICE] Milletari, Fausto, Nassir Navab, and Seyed-Ahmad Ahmadi. "V-net: Fully convolutional neural networks for volumetric medical image segmentation." 2016 Fourth International Conference on 3D Vision (3DV). IEEE, 2016.

• [IoU] Rahman, Md Atiqur, and Yang Wang. "Optimizing intersection-over-union in deep neural networks for image segmentation." International symposium on visual computing. Springer, Cham, 2016.

• [Tversky] Salehi, Seyed Sadegh Mohseni, Deniz Erdogmus, and Ali Gholipour. "Tversky loss function for image segmentation using 3D fully convolutional deep networks." International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 2017.

• [Tversky - Asym] Hashemi, Seyed Raein, et al. "Asymmetric loss functions and deep densely-connected networks for highly-imbalanced medical image segmentation: Application to multiple sclerosis lesion detection." IEEE Access 7 (2018): 1721-1735.

• [GD] Sudre, Carole H., et al. "Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations." Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, 2017. 240-248. (Generalized Dice loss)

• [pGD] Yang, Su, Jihoon Kweon, and Young-Hak Kim. "Major Vessel Segmentation on X-ray Coronary Angiography using Deep Networks with a Novel Penalty Loss Function." MILD Abstract (2019).

• [Focal Tversky] Abraham, Nabila, and Naimul Mefraz Khan. "A novel focal tversky loss function with improved attention U-Net for lesion segmentation." IEEE 16th International Symposium on Biomedical Imaging (ISBI) (2019). 

• [Log-cosh Dice] S. Jadon, "A survey of loss functions for semantic segmentation", 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), 2020. (also, Log-cosh dice loss)

Boundary-based Loss

• [Boundary loss] Kervadec, H., Bouchtiba, J., Desrosiers, C., Granger, E., Dolz, J. & Ben Ayed, I.. (2019). Boundary loss for highly unbalanced segmentation. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in PMLR 102:285-296 

• [Hausdorff Distance] Karimi, Davood, and Septimiu E. Salcudean. "Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks." TMI Early Access (2019).

  1. Weighted Hausdorff Distance

  2. Average Hausdorff Distance (AHD) 

• [Active Boundary Loss] C. Wang, Y. Zhang, M. Cui, P. Ren, Y. Yang, X. Xie, X. S. Hua, H. Bao, and W. Xu, "Active Boundary Loss for Semantic Segmentation", Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, No. 2, pp. 2397-2405, 2022.

• [Shape Aware Loss]

Hard-sample Mining

• [Pixel Hardness] X Xiao, D Zhou, J Hu, Y Hu, Y Xu, "Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation", arXiv preprint arXiv:2305.08462, 2023

Compounded Loss

• [Dice+CE] "Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation"

• [Dice+TopK] 

• [Dice+Focal] 

• [Dice+F-1] Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 3DV (2016)

• Taghanaki, S. A., Zheng, Y., Zhou, S. K., Georgescu, B., Sharma, P., Xu, D., ... & Hamarneh, G. "Combo loss: Handling input and output imbalance in multi-organ segmentation." Computerized Medical Imaging and Graphics 75 (2019): 24-33.

• Isensee, F., Petersen, J., Klein, A., Zimmerer, D., Jaeger, P. F., Kohl, S., ... & Maier-Hein, K. H. "nnu-net: Self-adapting framework for u-net-based medical image segmentation." arXiv preprint arXiv:1809.10486 (2018).

• [Dice Focal] Zhu, W., Huang, Y., Zeng, L., Chen, X., Liu, Y., Qian, Z., ... and Xie, X. "AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy." Medical physics 46.2 (2019): 576-589.

• [Exponential Logarithmic Loss] Wong, K.C., Moradi, M., Tang, H. and Syeda-Mahmood, T. "3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes". In: Frangi, A.F., et al., Eds., Medical Image Computing and Computer Assisted Intervention—MICCAI 2018, Springer, Cham, 612-619.

Unfilter

• Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax_CVPR_2020 [Paper] [Supp] [Slides] [Video] [Code and models] 

• J Ren, M Zhang, C Yu, Z Liu, "Balanced MSE for Imbalanced Visual Regression", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7926-7935, 2022.