mlsanityData to 7 Oct 2026

Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos

arXiv 2212.13495 ↗First posted 27 Dec 2022cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Learning with noisy label (LNL) is a classic problem that has been extensively studied for image tasks, but much less for video in the literature. A straightforward migration from images to videos without considering the properties of videos, such as computational cost and redundant information, is not a sound choice. In this paper, we propose two new strategies for video analysis with noisy labels: 1) A lightweight channel selection method dubbed as Channel Truncation for feature-based label noise detection. This method selects the most discriminative channels to split clean and noisy instances in each category; 2) A novel contrastive strategy dubbed as Noise Contrastive Learning, which constructs the relationship between clean and noisy instances to regularize model training. Experiments on three well-known benchmark datasets for video classification show that our proposed trubf Ncatbf E-split-contrbf Asbf T (NEAT) significantly outperforms the existing baselines. By reducing the dimension to 10% of it, our method achieves over 0.4 noise detection F1-score and 5% classification accuracy improvement on Mini-Kinetics dataset under severe noise (symmetric-80%). Thanks to Noise Contrastive Learning, the average classification accuracy improvement on Mini-Kinetics and Sth-Sth-V1 is over 1.6%.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 36 of its 41 references that are in the map. First posted on arXiv 27 Dec 2022.

Builds on

36 of 41 references.

References · 36

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  7. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  8. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  9. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  10. 2017A Closer Look at Memorization in Deep Networkscited by 936
  11. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  12. 2020What Makes for Good Views for Contrastive Learning?cited by 843
24 more
  1. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  2. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  3. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  4. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  5. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  6. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  7. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  8. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  9. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 259
  10. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  11. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  12. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  13. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  14. 2019Deep Self-Learning From Noisy Labelscited by 122
  15. 2019Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognitioncited by 117
  16. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
  17. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  18. 2020A Topological Filter for Learning with Label Noisecited by 76
  19. 2020Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learningcited by 66
  20. 2021Learning with Noisy Labels via Sparse Regularizationcited by 38
  21. 2021Continual Learning on Noisy Data Streams via Self-Purified Replaycited by 27
  22. 2019L_DMI: An Information-theoretic Noise-robust Loss Functioncited by 26
  23. 2020Temporal Distinct Representation Learning for Action Recognitioncited by 13
  24. 2021Searching for Robustness: Loss Learning for Noisy Classification Taskscited by 13

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Towards Long Video Understanding via Fine-detailed Video Story Generationcited by 6
  2. 2025Hierarchical Context Transformer for Multi-level Semantic Scene Understandingcited by 2
  3. 2024FlexPose: Pose Distribution Adaptation with Limited Guidancecited by 0
  4. 2025DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusioncited by 0