{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dynamic-loss-for-robust-learning","title":"Dynamic Loss For Robust Learning","arxiv_id":"2211.12506","date":"2022-11-22","proceeding":null,"authors":["Shenwang Jiang","Jianan Li","Jizhou Zhang","Ying Wang","Tingfa Xu"],"abstract":"Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperform when facing them both. To mitigate this gap, this work presents a novel meta-learning based dynamic loss that automatically adjusts the objective functions with the training process to robustly learn a classifier from long-tailed noisy data. Concretely, our dynamic loss comprises a label corrector and a margin generator, which respectively correct noisy labels and generate additive per-class classification margins by perceiving the underlying data distribution as well as the learning state of the classifier. Equipped with a new hierarchical sampling strategy that enriches a small amount of unbiased metadata with diverse and hard samples, the two components in the dynamic loss are optimized jointly through meta-learning and cultivate the classifier to well adapt to clean and balanced test data. Extensive experiments show our method achieves state-of-the-art accuracy on multiple real-world and synthetic datasets with various types of data biases, including CIFAR-10/100, Animal-10N, ImageNet-LT, and Webvision. Code will soon be publicly available.","url_abs":"https://arxiv.org/abs/2211.12506v2","url_pdf":"https://arxiv.org/pdf/2211.12506v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dynamic-loss-for-robust-learning","repo_url":"https://github.com/jiangwenj02/dynamic_loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"Dynamic Loss  (Inception-ResNet-v2)","rank_in_archive_order":9,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"74.76","ImageNet Top-5 Accuracy":"93.08","Top-1 Accuracy":"80.12","Top-5 Accuracy":"93.64"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","task":"Learning with noisy labels","dataset":"ANIMAL","model":"Dynamic Loss","rank_in_archive_order":8,"of":19,"metrics":{"Accuracy":"86.5","ImageNet Pretrained":"NO","Network":"Vgg19-BN"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.12506","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}