Data Augmented Flatness-aware Gradient Projection for Continual Learning
Abstract
The goal of continual learning (CL) is to continuously learn new tasks without forgetting previously learned old tasks. To alleviate catastrophic forgetting, gradient projection based CL methods require that the gradient updates of new tasks are orthogonal to the subspace spanned by old tasks. This limits the learning process and leads to poor performance on the new task due to the projection constraint being too strong. In this paper, we first revisit the gradient projection method from the perspective of flatness of loss surface, and find that unflatness of the loss surface leads to catastrophic forgetting of the old tasks when the projection constraint is reduced to improve the performance of new tasks. Based on our findings, we propose a Data Augmented Flatness-aware Gradient Projection (DFGP) method to solve the problem, which consists of three modules: data and weight perturbation, flatness-aware optimization, and gradient projection. Specifically, we first perform a flatness-aware perturbation on the task data and current weights to find the case that makes the task loss worst. Next, flatness-aware optimization optimizes both the loss and the flatness of the loss surface on raw and worst-case perturbed data to obtain a flatness-aware gradient. Finally, gradient projection updates the network with the flatness-aware gradient along directions orthogonal to the subspace of the old tasks. Extensive experiments on four datasets show that our method improves the flatness of loss surface and the performance of new tasks, and achieves state-of-the-art (SOTA) performance in the average accuracy of all tasks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
DFGP reinterprets the problem of catastrophic forgetting in orthogonal projection from the perspective of loss landscape flatness, and accordingly improves network flatness to balance plasticity and stability.
“DFGP (Yang et al., 2023, 2025) reinterprets the problem of catastrophic forgetting in orthogonal projection from the perspective of loss landscape flatness, and accordingly improves network flatness to balance plasticity and stability.”
From Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025) · cites this paper as Yang et al., 2023
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 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Wu, Y., & Vapnik, V. N. (1999) · Technometrics · doi:10.2307/1271368 · Cited by 27,236 · see citing works
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381 · see citing works
Overcoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899 · see citing works
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108 · see citing works
Matching Networks for One Shot LearningPreprint
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., & Wierstra, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04080 · Cited by 4,874 · see citing works
Reading digits in natural images with unsupervised feature learning
Netzer, Y. (2024) · doi:10.57702/e7wwo0zk · Cited by 4,261 · see citing works
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp MinimaPreprint
Keskar, N., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P. T. P. (2016) · International Conference on Learning Representations · doi:10.48550/arxiv.1609.04836 · Cited by 3,682 · see citing works
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117 · see citing works
Continual Learning Through Synaptic Intelligence
Zenke, F., Poole, B., & Ganguli, S. (2017) · arXiv · doi:10.48550/arxiv.1703.04200 · Cited by 1,784 · see citing works
Memory Aware Synapses: Learning What (not) to Forget
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., & Tuytelaars, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_9 · Cited by 1,590 · see citing works
Gradient Episodic Memory for Continual Learning
Lopez-Paz, D., & Ranzato, M. (2017) · arXiv · doi:10.48550/arxiv.1706.08840 · Cited by 1,403 · see citing works
Continual Learning with Deep Generative Replay
Shin, H., Lee, J. K., Kim, J., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1705.08690 · Cited by 1,385 · see citing works
Rusu, A. A., Rabinowitz, N. C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., & Hadsell, R. (2016) · arXiv · doi:10.48550/arxiv.1606.04671 · Cited by 1,307 · see citing works
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Mallya, A., & Lazebnik, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00810 · Cited by 1,258 · see citing works
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Chaudhry, A., Dokania, P. K., Ajanthan, T., & Torr, P. H. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_33 · Cited by 1,091 · see citing works
Ratcliff, R. (1990) · Psychological Review · doi:10.1037/0033-295x.97.2.285 · Cited by 892 · see citing works
Efficient Lifelong Learning with A-GEM
Chaudhry, A., Ranzato, M., Rohrbach, M., & Elhoseiny, M. (2018) · arXiv · doi:10.48550/arxiv.1812.00420 · Cited by 852 · see citing works
Averaging Weights Leads to Wider Optima and Better GeneralizationPreprint
Izmailov, P., Podoprikhin, D. A., Garipov, T., Vetrov, D., & Wilson, A. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.05407 · Cited by 818 · see citing works
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.1.1 · Cited by 704 · see citing works
Regularizing Neural Networks by Penalizing Confident Output Distributions
Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., & Hinton, G. (2017) · arXiv · doi:10.48550/arxiv.1701.06548 · Cited by 655 · see citing works
Mathematics for Machine Learning
Deisenroth, M. P., Faisal, A. A., & Ong, C. S. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108679930 · Cited by 583 · see citing works
Overcoming catastrophic forgetting with hard attention to the taskPreprint
Serr\`a, J., Surís, D., Miron, M., & Karatzoglou, A. (2018) · arXiv (Cornell University) · Cited by 564 · see citing works
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing InterferencePreprint
Riemer, M., Cases, I., Ajemian, R., Liu, M., Rish, I., Tu, Y., & Tesauro, G. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11910 · Cited by 534 · see citing works
Sharpness-Aware Minimization for Efficiently Improving Generalization
Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020) · arXiv · doi:10.48550/arxiv.2010.01412 · Cited by 521 · see citing works
Mermillod, M., Bugaïska, A., & Bonin, P. (2013) · Frontiers in Psychology · doi:10.3389/fpsyg.2013.00504 · Cited by 425 · see citing works
Gradient based sample selection for online continual learningPreprint
Aljundi, R., Lin, M., Goujaud, B., & Bengio, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.08671 · Cited by 397 · see citing works
Adversarial Weight Perturbation Helps Robust GeneralizationPreprint
Wu, D., Xia, S., & Wang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05884 · Cited by 390 · see citing works
Continual learning of context-dependent processing in neural networks
Zeng, G., Chen, Y., Cui, B., & Yu, S. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0080-x · Cited by 309 · cited 4× · see citing works
“To alleviate catastrophic forgetting of old tasks, several works [57, 15, 8, 27, 43] propose to constrain the gradient update direction of the new tasks.”
BackgroundInfluentialWortsman, M., Ilharco, G., Gadre, S. Y., Roelofs, R., Gontijo-Lopes, R., Morcos, A. S., Namkoong, H., Farhadi, A., Carmon, Y., Kornblith, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.05482 · Cited by 307 · see citing works
Zhang, X. (2011) · Encyclopedia of Machine Learning · doi:10.1007/978-0-387-30164-8_251 · Cited by 241 · see citing works
(2019) · arXiv (Cornell University) · Cited by 214 · see citing works
Overcoming catastrophic forgetting with hard attention to the task
Serrà, J., Surís, D., Miron, M., & Karatzoglou, A. (2018) · arXiv · doi:10.48550/arxiv.1801.01423 · Cited by 213 · see citing works
Orthogonal Gradient Descent for Continual LearningPreprint
Farajtabar, M., Azizan, N., Mott, A., & Li, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07104 · Cited by 184 · see citing works
Adversarial Continual Learning
Ebrahimi, S., Meier, F., Calandra, R., Darrell, T., & Rohrbach, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58621-8_23 · Cited by 178 · see citing works
How Does Mixup Help With Robustness and Generalization?Preprint
Zhang, L., Deng, Z., Kawaguchi, K., Ghorbani, A., & Zou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04819 · Cited by 134 · see citing works
Gradient Projection Memory for Continual Learning
Saha, G., Garg, I., & Roy, K. (2021) · arXiv · doi:10.48550/arxiv.2103.09762 · Cited by 129 · see citing works
Uncertainty-guided Continual Learning with Bayesian Neural NetworksPreprint
Ebrahimi, S., Elhoseiny, M., Darrell, T., & Rohrbach, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02425 · Cited by 123 · see citing works
Understanding the Role of Training Regimes in Continual LearningPreprint
Mirzadeh, S. I., Farajtabar, M., Pascanu, R., & Ghasemzadeh, H. G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06958 · Cited by 123 · see citing works
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
Wang, Z., Yang, E., Shen, L., & Huang, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3498346 · Cited by 101 · see citing works
Self-citationOvercoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat MinimaPreprint
Shi, G., Chen, J., Zhang, W., Zhan, L.-M., & Wu, X.-M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.01549 · Cited by 92 · see citing works
Towards Efficient and Scalable Sharpness-Aware Minimization
Liu, Y., Mai, S., Chen, X., Hsieh, C., & You, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01204 · Cited by 73 · see citing works
Representational Continuity for Unsupervised Continual LearningPreprint
Madaan, D., Yoon, J., Li, Y., Liu, Y., & Hwang, S. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06976 · Cited by 63 · see citing works
Continual Learning in Low-rank Orthogonal Subspaces
Chaudhry, A., Khan, N., Dokania, P. K., & Torr, P. H. S. (2020) · arXiv · doi:10.48550/arxiv.2010.11635 · Cited by 54 · see citing works
CPR: Classifier-Projection Regularization for Continual LearningPreprint
Cha, S., Hsu, H., Hwang, T., Calmon, F. P., & Moon, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07326 · Cited by 50 · see citing works
An Empirical Investigation of the Role of Pre-training in Lifelong LearningPreprint
Mehta, S. V., Patil, D., Chandar, S., & Strubell, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.09153 · Cited by 47 · see citing works
Sun, H., Shen, L., Zhong, Q., Ding, L., Chen, S., Sun, J., Li, J., Sun, G., & Tao, D. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.10.044 · Cited by 44 · see citing works
Self-citationTRGP: Trust Region Gradient Projection for Continual Learning
Lin, S., Yang, L., Fan, D., & Zhang, J. (2022) · arXiv · doi:10.48550/arxiv.2202.02931 · Cited by 43 · see citing works
Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual LearningPreprint
Deng, D., Chen, G., Hao, J., Wang, Q., & Heng, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.04593 · Cited by 41 · see citing works
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime InferencePreprint
Koh, H., Kim, D., Ha, J.-W., & Choi, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.10031 · Cited by 35 · see citing works
Balancing Stability and Plasticity Through Advanced Null Space in Continual Learning
Kong, Y., Liu, L., Wang, Z., & Tao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19809-0_13 · Cited by 32 · see citing works
Self-citationMake Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
Mi, P., Shen, L., Ren, T., Zhou, Y., Sun, X., Ji, R., & Tao, D. (2022) · neural information processing systems · doi:10.52202/068431-2244 · Cited by 30 · see citing works
Self-citationTowards Understanding Sharpness-Aware MinimizationPreprint
Andriushchenko, M., & Flammarion, N. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.06232 · Cited by 29 · see citing works
Catastrophic interference in connectionist networks: Can It Be predicted, can It be prevented?
French, R. M. (1993) · neural information processing systems · Cited by 27 · see citing works
Improving Task-free Continual Learning by Distributionally Robust Memory EvolutionPreprint
Wang, Z., Shen, L., Fang, L., Suo, Q., Duan, T., & Gao, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.07256 · Cited by 21 · see citing works
Self-citationLearning to Learn and Remember Super Long Multi-Domain Task Sequence
Wang, Z., Shen, L., Duan, T., Zhan, D., Fang, L., & Gao, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00782 · Cited by 21 · see citing works
Self-citationAn Introduction to Lifelong Supervised LearningPreprint
Sodhani, S., Faramarzi, M., Mehta, S. V., Malviya, P., Abdelsalam, M., Janarthanan, J., & Chandar, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.04354 · Cited by 8 · see citing works
Flagged first, then by citations
1 of the 59 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
Wang, Z., Yang, E., Shen, L., & Huang, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3498346 · Cited by 101 · see citing works
Self-citationContinual learning and catastrophic forgetting
van de Ven, G. M., Soures, N., & Kudithipudi, D. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-15754-7.00073-0 · Cited by 81 · see citing works
Ding, Y., Guo, B., Liu, Y., Jing, Y., Yin, M., Li, N., Wang, H., & Yu, Z. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103878 · Cited by 21 · see citing works
FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
Lee, G., Jeong, M., Kim, S., Oh, J., & Yun, S.-Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01189 · Cited by 21 · see citing works
Sharpness-aware gradient guidance for few-shot class-incremental learning
Chen, R., Jing, X., Wu, F., & Chen, H. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112030 · Cited by 13 · see citing works
Modeling Inner- and Cross-Task Contrastive Relations for Continual Image Classification
Luo, Y., Cong, R., Liu, X., Ip, H. H. S., & Kwong, S. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3414277 · Cited by 12 · see citing works
Revisiting Flatness-Aware Optimization in Continual Learning With Orthogonal Gradient Projection
Yang, E., Shen, L., Wang, Z., Liu, S., Guo, G., Wang, X., & Tao, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3539019 · Cited by 5 · see citing works
Self-citationAsk and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering
Marouf, I. E., Tartaglione, E., Lathuilière, S., & van de Weijer, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01680 · Cited by 4 · see citing works
Continual Learning From a Stream of APIs
Yang, E., Wang, Z., Shen, L., Yin, N., Liu, T., Guo, G., Wang, X., & Tao, D. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3460871 · Cited by 4 · see citing works
Self-citationCurvature Learning for Generalization of Hyperbolic Neural Networks
Fan, X., Wu, Y., Gao, Z. F., Harandi, M. T., & Jia, Y. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02567-4 · Cited by 2 · see citing works
Sparse and Expandable Network for Google's Pathways
Ling, C. X., Wang, G., & Wang, B. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1348030 · Cited by 1 · see citing works
Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
Phan, H., Tran, L., Tran, Q., Tran, N., Truong, T., Lei, Q., Ho, N., Phung, D., & Le, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00235 · Cited by 1 · see citing works
Geodesic-Aligned Gradient Projection for Continual Task Learning
Qiu, B., Qiu, H., Wen, H., Wang, L., Dai, Y., Meng, F., Wu, Q., & Li, H. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3551139 · Cited by 1 · see citing works
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models
Xu, H., Lan, P., Yang, E., Guo, G., Zhao, J., Jiang, L., & Wang, X. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.646
“DFGP (Yang et al., 2023, 2025) reinterprets the problem of catastrophic forgetting in orthogonal projection from the perspective of loss landscape flatness, and accordingly improves network flatness to balance plasticity and stability.”
Self-citationC-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning
Li, W., Yuan, H., Zhao, Z., Zhu, Y., Lu, A., Du, G., Sun, Y., & Feng, T. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03009-5
DeCO: A training-free framework for in-context knowledge editing via incremental reasoning
Xu, H., Liang, Y., Dang, Y., Guo, G., Zhao, J., Jiang, L., & Wang, X. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116292
Self-citationSTEP: Stable Gradient Projection for Continual Learning
Zhai, L., Tian, J., Yan, F., Su, L., Qin, Y., Jiang, S., Peng, C., & Zheng, P. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810725
Zhu, J., Fu, B., & Duan, G. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809714
SCoT: Similarity-Guided, Conflict-Aware Task Consolidation for Continual VQA
Patel, A., Abdar, M., & Banerjee, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_3
- Authors
- Yang, E., Shen, L., Wang, Z., Liu, S., Guo, G., & Wang, X.
- Affiliations
- Northeastern University (CN)
- Jingdong (China) (CN)
- University of Maryland, College Park (US)
- The University of Texas at Austin (US)
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 5607-5616
- OpenAlex
- W4390874035
- Cited by
- 18
- References
- 59
- Citations by year
- 2026: 5 · 2025: 5 · 2024: 8
- FWCI
- 3.19
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- continual learning, catastrophic forgetting, gradient projection, data augmentation, weight perturbation, worst-case perturbations
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
