AI Paper Atlas

Research map / Benchmarks / WebVision

WebVision leaderboard

39 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WebVision. Best accuracy: 87.44 (TANGO, CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

WebVision · accuracy

28 papers, each with its best reported number for its own method; higher is better.

18 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

WebVision · accuracy (val)

11 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
181.1DPC*
InceptionResNetV2
Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
AAAI 2024 · Table 3
Noisy labels
279.5NCENeighborhood Collective Estimation for Noisy Label Identification and Correction
ECCV 2022 · Table 3
Noisy labels
379.4Ours
Inception-ResNet V2
Faster Meta Update Strategy for Noise-Robust Deep Learning
CVPR 2021 · Table 5
Noisy labels
479.28GJS, two networks
ResNet-50
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
NeurIPS 2021 · Table 2
Noisy labels
578.1NoiseGPT+DivideMix
Inception-ResNet v2
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
NeurIPS 2024 · Table 5
Noisy labels
677.6UniCon
InceptionResNetV2
UniCon: Combating Label Noise Through Uniform Selection and Contrastive Learning
CVPR 2022 · Table: WebVision and ILSVRC12
Noisy labels
777.32DivideMix
Inception-ResNet-v2
DivideMix: Learning with Noisy Labels as Semi-supervised Learning
ICLR 2020 · Table 4
Semi-supervised learning
873.81Early Cutting
ResNet-50
Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
NeurIPS 2025 · large-scale datasets table
Noisy labels
969.14CleanNet, all-1000
ResNet-50
CleanNet: Transfer Learning for Scalable Image Classifier Training With Label Noise
CVPR 2018 · Table: Image classification on
Noisy labels
1068.32ANL-FLActive Negative Loss Functions for Learning with Noisy Labels
NeurIPS 2023 · Table 3
Noisy labels
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.