The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Open accessAbstract
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$. We find a majority of loss functions, including the triplet loss and the softmax cross-entropy loss, embed $s_n$ and $s_p$ into similarity pairs and seek to reduce $(s_n-s_p)$. Such an optimization manner is inflexible, because the penalty strength on every single similarity score is restricted to be equal. Our intuition is that if a similarity score deviates far from the optimum, it should be emphasized. To this end, we simply re-weight each similarity to highlight the less-optimized similarity scores. It results in a Circle loss, which is named due to its circular decision boundary. The Circle loss has a unified formula for two elemental deep feature learning paradigms, \emph {i.e.}, learning with class-level labels and pair-wise labels. Analytically, we show that the Circle loss offers a more flexible optimization approach towards a more definite convergence target, compared with the loss functions optimizing $(s_n-s_p)$. Experimentally, we demonstrate the superiority of the Circle loss on a variety of deep feature learning tasks. On face recognition, person re-identification, as well as several fine-grained image retrieval datasets, the achieved performance is on par with the state of the art.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
Dimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
Huang, G. B., Mattar, M., Berg, T. L., & Miller, E. G. (2008) · HAL · Cited by 4,822
Scalable Person Re-identification: A Benchmark
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.133 · Cited by 4,506
Self-citationA Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077
Learning a Similarity Metric Discriminatively, with Application to Face Verification
Chopra, S., Hadsell, R., & LeCun, Y. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.202 · Cited by 4,036
Research works printed but not linked: 2
- liu, 0, Large-margin softmax loss for convolutional neural networks, Proceedings of the 33rd International Conference on Machine Learning, 507
- zheng, 0, Joint discriminative and generative learning for person reidentification, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Cited by
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
TransReID: Transformer-based Object Re-Identification
He, S., Luo, H., Wang, P., Wang, F., Li, H., & Jiang, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01474 · Cited by 1,244
PREDATOR: Registration of 3D Point Clouds with Low Overlap
Huang, S., Gojcic, Z., Usvyatsov, M., Wieser, A., & Schindler, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00425 · Cited by 721
MagFace: A Universal Representation for Face Recognition and Quality Assessment
Meng, Q., Zhao, S., Huang, Z., & Zhou, F. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01400 · Cited by 625
Geometric Transformer for Fast and Robust Point Cloud Registration
Qin, Z., Yu, H., Wang, C., Guo, Y., Peng, Y., & Xu, K. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01086 · Cited by 505
Quasi-Dense Similarity Learning for Multiple Object Tracking
Pang, J., Qiu, L., Li, X., Chen, H., Li, Q., Darrell, T., & Yu, F. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00023 · Cited by 480
“supervise dense matched quasi-dense samples with multiple positive contrastive learning by the inspiration of [42].”
BackgroundA Metric Learning Reality Check
Musgrave, K., Belongie, S., & Lim, S.-N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58595-2_41 · Cited by 414
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Rao, Y., Chen, G., Lu, J., & Zhou, J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00106 · Cited by 380
Channel Augmented Joint Learning for Visible-Infrared Recognition
Ye, M., Ruan, W., Du, B., & Shou, M. Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01331 · Cited by 375
A comprehensive survey of loss functions and metrics in deep learning
Terven, J., Cordova-Esparza, D.-M., Romero-González, J.-A., Ramírez-Pedraza, A., & Chávez-Urbiola, E. A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11198-7 · Cited by 343
Self-Alignment Pretraining for Biomedical Entity Representations
Liu, F., Shareghi, E., Meng, Z., Basaldella, M., & Collier, N. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.334 · Cited by 335
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
Ge, Y., Zhu, F., Chen, D., Zhao, R., & Li, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02713 · Cited by 329
Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification
Wu, Q., Dai, P., Chen, J., Lin, C.-W., Wu, Y., Huang, F., Zhong, B., & Ji, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00431 · Cited by 313
Yang, Y., Zhuang, Y., & Pan, Y. (2021) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2100463 · Cited by 309
ElasticFace: Elastic Margin Loss for Deep Face Recognition
Boutros, F., Damer, N., Kirchbuchner, F., & Kuijper, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00164 · Cited by 294
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
Zhu, Z., Huang, G., Deng, J., Ye, Y., Huang, J., Chen, X., Zhu, J., Yang, T., Lu, J., Du, D., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01035 · Cited by 290
GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer
Qin, Z., Yu, H., Wang, C., Guo, Y., Peng, Y., Ilic, S., Hu, D., & Xu, K. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3259038 · Cited by 279
REGTR: End-to-end Point Cloud Correspondences with Transformers
Yew, Z. J., & Lee, G. H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00656 · Cited by 277
Clothes-Changing Person Re-identification with RGB Modality Only
Gu, X., Chang, H., Ma, B., Bai, S., Shan, S., & Chen, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00113 · Cited by 256
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild
Fard, A. P., & Mahoor, M. H. (2022) · IEEE Access · doi:10.1109/access.2022.3156598 · Cited by 157
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Xu, H., Yan, M., Li, C., Bi, B., Huang, S., Xiao, W., & Huang, F. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.42 · Cited by 84
“We use the hidden state of h to compute the similarity scores for the sampled positive and negative pairs, and maximize the margin between them through circle loss (Sun et al., 2020) as ERNIE-ViL (Yu et al., 2020).”
MethodSemi-Supervised Contrastive Learning With Similarity Co-Calibration
Zhang, Y., Zhang, X., Li, J., Qiu, R. C., Xu, H., & Tian, Q. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3158069 · Cited by 67
Self-citationForgery-Aware Adaptive Learning With Vision Transformer for Generalized Face Forgery Detection
Luo, A., Cai, R., Kong, C., Ju, Y., Kang, X., Huang, J., & Kot, A. C. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3522091 · Cited by 41
MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain
Chase, T., & Dantu, K. (2024) · arXiv · doi:10.48550/arxiv.2410.05182 · Cited by 5
Metadata
- Authors
- Sun, Y., Cheng, C., Zhang, Y., Zhang, C., Zheng, L., Wang, Z., & Wei, Y.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 6397-6406
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3034303554
- Cited by
- 987
- References
- 43
- FWCI
- 61.28
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.