SpringerLink
Log in

Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13694))

Included in the following conference series:

  • 2068 Accesses

Abstract

This paper focuses on the weakly-supervised audio-visual video parsing task, which aims to recognize all events belonging to each modality and localize their temporal boundaries. This task is challenging because only overall labels indicating the video events are provided for training. However, an event might be labeled but not appear in one of the modalities, which results in a modality-specific noisy label problem. In this work, we propose a training strategy to identify and remove modality-specific noisy labels dynamically. It is motivated by two key observations: 1) networks tend to learn clean samples first; and 2) a labeled event would appear in at least one modality. Specifically, we sort the losses of all instances within a mini-batch individually in each modality, and then select noisy samples according to the relationships between intra-modal and inter-modal losses. Besides, we also propose a simple but valid noise ratio estimation method by calculating the proportion of instances whose confidence is below a preset threshold. Our method makes large improvements over the previous state of the arts (e.g., from 60.0% to 63.8% in segment-level visual metric), which demonstrates the effectiveness of our approach. Code and trained models are publicly available at https://github.com/MCG-NJU/JoMoLD.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Alwassel, H., Mahajan, D., Korbar, B., Torresani, L., Ghanem, B., Tran, D.: Self-supervised learning by cross-modal audio-video clustering. In: 34th Conference on Neural Information Processing Systems (NeurIPS 2020). NeurIPS (2020)

    Google Scholar 

  2. Amrani, E., Ben-Ari, R., Rotman, D., Bronstein, A.: Noise estimation using density estimation for self-supervised multimodal learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 35, pp. 6644–6652 (2021)

    Google Scholar 

  3. Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 609–617 (2017)

    Google Scholar 

  4. Arandjelovic, R., Zisserman, A.: Objects that sound. In: Proceedings of the European conference on computer vision (ECCV), pp. 435–451 (2018)

    Google Scholar 

  5. Arazo, E., Ortego, D., Albert, P., O’Connor, N., McGuinness, K.: Unsupervised label noise modeling and loss correction. In: International Conference on Machine Learning, pp. 312–321. PMLR (2019)

    Google Scholar 

  6. Arpit, D., et al.: A closer look at memorization in deep networks. In: International Conference on Machine Learning, pp. 233–242. PMLR (2017)

    Google Scholar 

  7. Aytar, Y., Vondrick, C., Torralba, A.: Soundnet: learning sound representations from unlabeled video. Adv. Neural Inf. Process. Syst. 29, 892–900 (2016)

    Google Scholar 

  8. Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings of the eleventh annual conference on Computational learning theory, pp. 92–100 (1998)

    Google Scholar 

  9. Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Trans. Grap. (TOG) 37(4), 1–11 (2018)

    Article  Google Scholar 

  10. Gao, R., Grauman, K.: Visualvoice: Audio-visual speech separation with cross-modal consistency. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15495–15505 (2021)

    Google Scholar 

  11. Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: Action recognition by previewing audio. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10457–10467 (2020)

    Google Scholar 

  12. Gupta, S., Hoffman, J., Malik, J.: Cross modal distillation for supervision transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2827–2836 (2016)

    Google Scholar 

  13. Han, B., et.al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 8536–8546 (2018)

    Google Scholar 

  14. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  15. Hershey, S., et al.: Cnn architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (icassp), pp. 131–135. IEEE (2017)

    Google Scholar 

  16. Hori, C., et.al.: Attention-based multimodal fusion for video description. In: Proceedings of the IEEE international conference on computer vision, pp. 4193–4202 (2017)

    Google Scholar 

  17. Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9248–9257 (2019)

    Google Scholar 

  18. Hu, P., Peng, X., Zhu, H., Zhen, L., Lin, J.: Learning cross-modal retrieval with noisy labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5403–5413 (2021)

    Google Scholar 

  19. Kim, Y., Yun, J., Shon, H., Kim, J.: Joint negative and positive learning for noisy labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9442–9451 (2021)

    Google Scholar 

  20. Korbar, B., Tran, D., Torresani, L.: Cooperative learning of audio and video models from self-supervised synchronization. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 7774–7785 (2018)

    Google Scholar 

  21. Li, J., Socher, R., Hoi, S.C.H.: Dividemix: Learning with noisy labels as semi-supervised learning. Ar**v abs/2002.07394 (2020)

    Google Scholar 

  22. Li, M., Soltanolkotabi, M., Oymak, S.: Gradient descent with early stop** is provably robust to label noise for overparameterized neural networks. In: The 23rd International Conference on Artificial Intelligence and Statistics (2020)

    Google Scholar 

  23. Lin, Y.B., Li, Y.J., Wang, Y.C.F.: Dual-modality seq2seq network for audio-visual event localization. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2002–2006. IEEE (2019)

    Google Scholar 

  24. Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1298–1307 (2019)

    Google Scholar 

  25. Liu, S., Niles-Weed, J., Razavian, N., Fernandez-Granda, C.: Early-learning regularization prevents memorization of noisy labels. Adv. Neural Inf. Process. Sys. 33 (2020)

    Google Scholar 

  26. Malach, E., Shalev-Shwartz, S.: Decoupling“ when to update” from“ how to update”. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 961–971 (2017)

    Google Scholar 

  27. Mandal, D., Bharadwaj, S., Biswas, S.: A novel self-supervised re-labeling approach for training with noisy labels. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1381–1390 (2020)

    Google Scholar 

  28. Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752–6761 (2018)

    Google Scholar 

  29. Nguyen, T., Mummadi, C., Ngo, T., Beggel, L., Brox, T.: Self: learning to filter noisy labels with self-ensembling. In: International Conference on Learning Representations (ICLR) (2020)

    Google Scholar 

  30. Panda, R., et al.: Adamml: Adaptive multi-modal learning for efficient video recognition. ar**v preprint ar**v:2105.05165 (2021)

  31. Pedro Morgado, Nuno Vasconcelos, I.M.: Audio-visual instance discrimination with cross-modal agreement. In: Computer Vision and Pattern Recognition (CVPR), IEEE/CVF Conf. on (2021)

    Google Scholar 

  32. Rahman, T., Xu, B., Sigal, L.: Watch, listen and tell: Multi-modal weakly supervised dense event captioning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8908–8917 (2019)

    Google Scholar 

  33. Senocak, A., Oh, T.H., Kim, J., Yang, M.H., Kweon, I.S.: Learning to localize sound source in visual scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4358–4366 (2018)

    Google Scholar 

  34. Song, H., Kim, M., Lee, J.G.: Selfie: Refurbishing unclean samples for robust deep learning. In: International Conference on Machine Learning, pp. 5907–5915. PMLR (2019)

    Google Scholar 

  35. Tanaka, D., Ikami, D., Yamasaki, T., Aizawa, K.: Joint optimization framework for learning with noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5552–5560 (2018)

    Google Scholar 

  36. Tian, Y., Guan, C., Goodman, J., Moore, M., Xu, C.: An attempt towards interpretable audio-visual video captioning. ar**v preprint ar**v:1812.02872 (2018)

  37. Tian, Y., Li, D., Xu, C.: Unified multisensory perception: weakly-supervised audio-visual video parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 436–454. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_26

    Chapter  Google Scholar 

  38. Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 247–263 (2018)

    Google Scholar 

  39. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6450–6459 (2018)

    Google Scholar 

  40. Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., Bailey, J.: Symmetric cross entropy for robust learning with noisy labels. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 322–330 (2019)

    Google Scholar 

  41. Wang, Y., Li, J., Metze, F.: A comparison of five multiple instance learning pooling functions for sound event detection with weak labeling. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 31–35. IEEE (2019)

    Google Scholar 

  42. Wei, H., Feng, L., Chen, X., An, B.: Combating noisy labels by agreement: A joint training method with co-regularization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13726–13735 (2020)

    Google Scholar 

  43. Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1326–1335 (2021)

    Google Scholar 

  44. Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 6292–6300 (2019)

    Google Scholar 

  45. **ao, F., Lee, Y.J., Grauman, K., Malik, J., Feichtenhofer, C.: Audiovisual slowfast networks for video recognition. ar**v preprint ar**v:2001.08740 (2020)

  46. Yi, K., Wu, J.: Probabilistic end-to-end noise correction for learning with noisy labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7017–7025 (2019)

    Google Scholar 

  47. Yu, X., Han, B., Yao, J., Niu, G., Tsang, I., Sugiyama, M.: How does disagreement help generalization against label corruption? In: International Conference on Machine Learning, pp. 7164–7173. PMLR (2019)

    Google Scholar 

  48. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization (2016). ar**v preprint ar**v:1611.03530 (2017)

  49. Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: 32nd Conference on Neural Information Processing Systems (NeurIPS) (2018)

    Google Scholar 

  50. Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 570–586 (2018)

    Google Scholar 

  51. Zhou, H., Xu, X., Lin, D., Wang, X., Liu, Z.: Sep-stereo: visually guided stereophonic audio generation by associating source separation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 52–69. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_4

    Chapter  Google Scholar 

  52. Zhou, J., Zheng, L., Zhong, Y., Hao, S., Wang, M.: Positive sample propagation along the audio-visual event line. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8436–8444 (2021)

    Google Scholar 

Download references

Acknowledgements

This work is supported by National Natural Science Foundation of China (No.62076119, No.61921006), Program for Innovative Talents and Entrepreneur in Jiangsu Province, and Collaborative Innovation Center of Novel Software Technology and Industrialization.

Author information

Authors and Affiliations

  1. State Key Laboratory for Novel Software Technology, Nan**g University, Nan**g, China

    Haoyue Cheng & Limin Wang

  2. SenseTime Research, Shanghai, China

    Haoyue Cheng, Zhaoyang Liu, Chen Qian & Wayne Wu

  3. CUHK - Sensetime Joint Lab, Hong Kong, China

    Hang Zhou

  4. Shanghai AI Laboratory, Shanghai, China

    Limin Wang

Authors
  1. Haoyue Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhaoyang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chen Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wayne Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Limin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Limin Wang .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1286 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cheng, H., Liu, Z., Zhou, H., Qian, C., Wu, W., Wang, L. (2022). Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13694. Springer, Cham. https://doi.org/10.1007/978-3-031-19830-4_25

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19830-4_25

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19829-8

  • Online ISBN: 978-3-031-19830-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation