Papers › Dynamic Loss For Robust Learning

Dynamic Loss For Robust Learning

22 Nov 2022arXiv:2211.12506archive 2025-07-28

Shenwang Jiang, Jianan Li, Jizhou Zhang, Ying Wang, Tingfa Xu

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jiangwenj02/dynamic_loss officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationLearning with noisy labelsMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification mini WebVision 1.0 Dynamic Loss (Inception-ResNet-v2) ImageNet Top-1 Accuracy 74.76 #9 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 Dynamic Loss (Inception-ResNet-v2) ImageNet Top-5 Accuracy 93.08 #9 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 Dynamic Loss (Inception-ResNet-v2) Top-1 Accuracy 80.12 #9 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 Dynamic Loss (Inception-ResNet-v2) Top-5 Accuracy 93.64 #9 of 47 Archive leaderboard report
Learning with noisy labels ANIMAL Dynamic Loss Accuracy 86.5 #8 of 19 Archive leaderboard report
Learning with noisy labels ANIMAL Dynamic Loss ImageNet Pretrained NO #8 of 19 Archive leaderboard report
Learning with noisy labels ANIMAL Dynamic Loss Network Vgg19-BN #8 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Test

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections