Skip to main content

Advertisement

Springer Nature Link
Log in

Multi-label noisy samples in underwater inspection from the oil and gas industry

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Deep learning has shown remarkable success in various machine learning tasks, including multi-label classification. Multi-label classification is a supervised task where an input instance can be associated with multiple labels simultaneously, instead of exclusively one, as in the single-label scenario. When building a multi-label dataset for real-world applications, a recurrent problem is the presence of noisy labels. In this context, noisy labels refer to mislabeled data, which can potentially weaken the performance of supervised models. Although this issue may be well explored for single-label noise, it is still an emerging topic for multi-label applications. In this work, a novel deep learning model that handles multi-label noise is proposed, where we combine the Small Loss Approach Multi-label (SLAM) with a joint loss, in order to automatically identify and rectify noisy labels. The model outperforms in \(2.5\%\) for the F1-score state-of-the-art (SOTA) models in the noisy version of the benchmark UcMerced. A new open noisy version of the benchmark TreeSATAI was developed and is now disclosed, where the performance gains reached \(1.8\%\) in F-1 Score. Furthermore, the model was able to reduce the presence of noise from \(25\%\) to \(5\%\) in both sets. In addition, we evaluate the model on a real-world application of underwater inspections, to assist with the multi-label classification for an oil and gas company. Our model achieved gains in the F1-Score of \(10\%\) when compared to a standard model (without noise-handling techniques), and up to \(2.7\%\) and \(1.9\%\) when compared to SOTA models SLAM and JoCoR, respectively.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Algorithm 1
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability Statement

The benchmark dataset TreeSatAI used to evaluate our model is available in:https://zenodo.org/records/6598391 and the noisy labels available in the link: https://github.com/ICA-PUC/TreeSatAINoiseDataset; The benchmark dataset UcMerced used to evaluate our model is available in: http://weegee.vision.ucmerced.edu/datasets/landuse.html and the noisy labels available in: https://github.com/ICA-PUC/UcMercedNoiseDataset The dataset used in the real application of our model is private data, and in respect to the determinations of the data owners it will not be turn public, for corporate reasons. The code used for models Slam by joint loss will not be turn public due the determinations of the data owners, for corporate reasons.

References

  1. You A, Kim JK, Ryu IH, Yoo TK (2022) Application of generative adversarial networks (gan) for ophthalmology image domains: a survey. Eye Vis 9(1):1–19

    Article  Google Scholar 

  2. Baek M, Baker D (2022) Deep learning and protein structure modeling. Nature Methods 19(1):13–14

    Article  CAS  PubMed  Google Scholar 

  3. Yusoff M, Haryanto T, Suhartanto H, Mustafa WA, Zain JM, Kusmardi K (2023) Accuracy analysis of deep learning methods in breast cancer classification: A structured review. Diagnostics 13(4):683

    Article  PubMed  PubMed Central  Google Scholar 

  4. Yu J, Yin H, Xia X, Chen T, Li J, Huang Z (2023) Self-supervised learning for recommender systems: a survey. IEEE Trans Knowl Data Eng 23:535

    Google Scholar 

  5. Liu W, Wang H, Shen X, Tsang IW (2021) The emerging trends of multi-label learning. IEEE Trans Patt Anal Mach Intell 44(11):7955–7974

    Article  Google Scholar 

  6. Haghighian Roudsari A, Afshar J, Lee W, Lee S (2022) Patentnet: multi-label classification of patent documents using deep learning based language understanding. Scientometrics 1:1–25

    Google Scholar 

  7. Kaselimi M, Voulodimos A, Daskalopoulos I, Doulamis N, Doulamis A (2022) A vision transformer model for convolution-free multilabel classification of satellite imagery in deforestation monitoring. IEEE Trans Neural Netw Learn Syst 2:003

    Google Scholar 

  8. Cheng X, Lin H, Wu X, Shen D, Yang, F, Liu H, Shi N Mltr: Multi-label classification with transformer. In: 2022 IEEE international conference on multimedia and expo (ICME), pp. 1–6 (2022). IEEE

  9. Han B, Yao Q, Yu X, Niu G, Xu M, Hu W, Tsang I, Sugiyama M (2018) Co-teaching: Robust training of deep neural networks with extremely noisy labels. Adv Neural Inform Process Syst 31:355

    Google Scholar 

  10. Wei H, Feng L, Chen X, An B (2020) 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

  11. Yao Y, Sun Z, Zhang C, Shen F, Wu Q, Zhang J, Tang Z (2021) Jo-src: a contrastive approach for combating noisy labels. In: proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5192–5201

  12. Yu X, Han B, Yao J, Niu G, Tsang I, Sugiyama M (2019) How does disagreement help generalization against label corruption? In: international conference on machine learning, pp. 7164–7173 PMLR

  13. Huang L, Zhang C, Zhang H (2021) Self-adaptive training: bridging the supervised and self-supervised learning. arXiv preprint arXiv:2101.08732

  14. Burgert T, Ravanbakhsh M, Demir B (2022) On the effects of different types of label noise in multi-label remote sensing image classification. IEEE Trans Geosci Remote Sens 60:1–13

    Article  Google Scholar 

  15. Sousa V, Pereira AL, Kohler M, Pacheco M Learning by small loss approach multi-label to deal with noisy labels. In: International Conference on Computational Science and Its Applications, pp. 385–403 (2023). Springer

  16. Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PH (2016) Fully-convolutional siamese networks for object tracking. In: computer vision–ECCV 2016 workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14, pp. 850–865 . Springer

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

  18. Yang Y, Newsam S (2010) Bag-of-visual-words and spatial extensions for land-use classification. In: proceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems, pp. 270–279

  19. Ahlswede S, Schulz C, Gava C, Helber P, Bischke B, Förster M, Arias F, Hees J, Demir B, Kleinschmit B (2022) Treesatai benchmark archive: a multi-sensor, multi-label dataset for tree species classification in remote sensing. Earth Syst Sci Data Discuss 2022:1–22

    Google Scholar 

  20. Wei T, Shi JX, Tu WW, Li YF (2021) Robust long-tailed learning under label noise. arXiv preprint arXiv:2108.11569

  21. Ghosh A, Kumar H, Sastry PS (2017) Robust loss functions under label noise for deep neural networks. In: proceedings of the AAAI conference on artificial intelligence, vol. 31

  22. Liu S, Niles-Weed J, Razavian N, Fernandez-Granda C (2020) Early-learning regularization prevents memorization of noisy labels. Adv Neural Inform Process Syst 33:20331–20342

    Google Scholar 

  23. Sun Z, Shen F, Huang D, Wang Q, Shu X, Yao Y, Tang J (2022) Pnp: Robust learning from noisy labels by probabilistic noise prediction. In: proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5311–5320

  24. Inoue N, Simo-Serra E, Yamasaki T, Ishikawa H (2017) Multi-label fashion image classification with minimal human supervision. In: proceedings of the IEEE international conference on computer vision workshops, pp. 2261–2267

  25. Hu M, Han, H, Shan S, Chen X (2019) Multi-label learning from noisy labels with non-linear feature transformation. In: computer vision–ACCV 2018: 14th asian conference on computer vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part V 14, pp. 404–419 Springer

  26. Menéndez M, Pardo J, Pardo L, Pardo M (1997) The jensen-shannon divergence. J Frank Inst 334(2):307–318

    Article  MathSciNet  Google Scholar 

  27. Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2021) Understanding deep learning (still) requires rethinking generalization. Commun ACM 64(3):107–115

    Article  Google Scholar 

  28. Khosla P, Teterwak P, Wang C, Sarna A, Tian Y, Isola P, Maschinot A, Liu C, Krishnan D (2020) Supervised contrastive learning. Adv Neural Inform Process Syst 33:18661–18673

    Google Scholar 

  29. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556

  30. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248–255. Ieee

  31. Kingma DP, Ba J (2014)Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

Download references

Acknowledgements

The authors would like to thank Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq), Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (Capes), and Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio) for their financial support.

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Pontifícia Universidade Católica, R. Marquês de São Vicente, 225, Rio de Janeiro, 22451–900, Rio de Janeiro, Brazil

    First Vitor Sousa, Second Amanda Pereira, Third Manoela Koher & Fourth Marco Pacheco

Authors
  1. First Vitor Sousa
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Second Amanda Pereira
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Third Manoela Koher
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Fourth Marco Pacheco
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to First Vitor Sousa.

Ethics declarations

Conflict of interest

All authors state that there is no conflict of interest

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sousa, F.V., Pereira, S.A., Koher, T.M. et al. Multi-label noisy samples in underwater inspection from the oil and gas industry. Neural Comput & Applic 36, 6855–6873 (2024). https://doi.org/10.1007/s00521-024-09434-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-024-09434-2

Keyword