mlsanityData to 14 Oct 2026

Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label

arXiv 2604.23125 ↗First posted 25 Apr 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress in addressing this combined challenge, it overlooks the severe label-image mismatch inherent to high-noise settings, thereby limiting their effectiveness. Given that observed labels, though mismatched with images, still retain category information, we propose employing auxiliary text information from labels to address label-image inconsistencies in long-tailed noisy data. Specifically, we leverage the intrinsic cross-modal alignment in pre-trained visual-language models to correct the label-image inconsistencies. This supervisory signal, referred to as Weak Teacher Supervision (WTS), is unaffected by label noise and data distribution biases, albeit exhibits limited accuracy. Therefore, the activation of WTS is determined by evaluating the discrepancy between text-predicted labels and observed labels. Extensive experiments demonstrate the superior performance of WTS across synthetic and real-world datasets, particularly under high-noise conditions. The source code is available at https://anonymous.4open.science/r/WTS-0F3C.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 67 references that are in the map. First posted on arXiv 25 Apr 2026.

Builds on

52 of 67 references.

References · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  5. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  7. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  8. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 968
  9. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  10. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  11. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  12. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
38 more
  1. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  2. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  3. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  4. 2020Long-tail learning via logit adjustmentcited by 618
  5. 2021Deep Long-Tailed Learning: A Surveycited by 417
  6. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  7. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  8. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  9. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  10. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  11. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
  12. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  13. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  14. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  15. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  16. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  17. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  18. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  19. 2021Influence-Balanced Loss for Imbalanced Visual Classificationcited by 91
  20. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  21. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  22. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  23. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  24. 2020MoPro: Webly Supervised Learning with Momentum Prototypescited by 66
  25. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  26. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  27. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  28. 2021Trustworthy Long-Tailed Classificationcited by 51
  29. 2020Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularizationcited by 49
  30. 2021Robust Long-Tailed Learning under Label Noisecited by 36
  31. 2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
  32. 2023Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learningcited by 22
  33. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  34. 2022Identifying Hard Noise in Long-Tailed Sample Distributioncited by 19
  35. 2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
  36. 2021Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Datacited by 16
  37. 2021Prototypical Classifier for Robust Class-Imbalanced Learningcited by 10
  38. 2024FedFixer: Mitigating Heterogeneous Label Noise in Federated Learningcited by 8

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.