Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

DAS: Densely-Anchored Sampling for Deep Metric Learning

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13686))

Included in the following conference series:

  • 3299 Accesses

Abstract

Deep Metric Learning (DML) serves to learn an embedding function to project semantically similar data into nearby embedding space and plays a vital role in many applications, such as image retrieval and face recognition. However, the performance of DML methods often highly depends on sampling methods to choose effective data from the embedding space in the training. In practice, the embeddings in the embedding space are obtained by some deep models, where the embedding space is often with barren area due to the absence of training points, resulting in so called “missing embedding” issue. This issue may impair the sample quality, which leads to degenerated DML performance. In this work, we investigate how to alleviate the “missing embedding” issue to improve the sampling quality and achieve effective DML. To this end, we propose a Densely-Anchored Sampling (DAS) scheme that considers the embedding with corresponding data point as “anchor” and exploits the anchor’s nearby embedding space to densely produce embeddings without data points. Specifically, we propose to exploit the embedding space around single anchor with Discriminative Feature Scaling (DFS) and multiple anchors with Memorized Transformation Shifting (MTS). In this way, by combing the embeddings with and without data points, we are able to provide more embeddings to facilitate the sampling process thus boosting the performance of DML. Our method is effortlessly integrated into existing DML frameworks and improves them without bells and whistles. Extensive experiments on three benchmark datasets demonstrate the superiority of our method.

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
$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

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 shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Visualization of the frequency recorder matrix is in the supplementary.

  2. 2.

    See supplementary for detailed DML sampling methods and loss functions.

  3. 3.

    See supplementary for more details.

  4. 4.

    Experiments on hyper-parameters \(T, r_s, r_b\) are in the supplementary.

  5. 5.

    Results on more pair-based losses are in the supplementary.

  6. 6.

    More qualitative results are in the supplementary.

References

  1. Aziere, N., Todorovic, S.: Ensemble deep manifold similarity learning using hard proxies. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7299–7307 (2019)

    Google Scholar 

  2. Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6541–6549 (2017)

    Google Scholar 

  3. Bau, D., Zhu, J.Y., Strobelt, H., Lapedriza, A., Zhou, B., Torralba, A.: Understanding the role of individual units in a deep neural network. Proc. Natl. Acad. Sci. 117(48), 30071–30078 (2020)

    Article  Google Scholar 

  4. Ko, B., Gu, G., Kim, H.G.: Learning with memory-based virtual classes for deep metric learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)

    Google Scholar 

  5. Chen, P., et al.: RSPNet: relative speed perception for unsupervised video representation learning. In: AAAI Conference on Artificial Intelligence 2021 (2021)

    Google Scholar 

  6. Chen, P., Zhang, Y., Tan, M., Xiao, H., Huang, D., Gan, C.: Generating visually aligned sound from videos. IEEE Trans. Image Process. 29, 8292–8302 (2020)

    Article  MATH  Google Scholar 

  7. Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 403–412 (2017)

    Google Scholar 

  8. Chu, P., Bian, X., Liu, S., Ling, H.: Feature space augmentation for long-tailed data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 694–710. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58526-6_41

    Chapter  Google Scholar 

  9. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  10. Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690–4699 (2019)

    Google Scholar 

  11. DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538 (2017)

  12. Ding, Z., Fu, Y.: Robust transfer metric learning for image classification. IEEE Trans. Image Process. 26(2), 660–670 (2016)

    Article  MathSciNet  MATH  Google Scholar 

  13. Duan, Y., Zheng, W., Lin, X., Lu, J., Zhou, J.: Deep adversarial metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2780–2789 (2018)

    Google Scholar 

  14. Escorcia, V., Carlos Niebles, J., Ghanem, B.: On the relationship between visual attributes and convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1256–1264 (2015)

    Google Scholar 

  15. Ge, W., Huang, W., Dong, D., Scott, M.R.: Deep metric learning with hierarchical triplet loss. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 272–288. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_17

    Chapter  Google Scholar 

  16. Gu, G., Ko, B., Kim, H.G.: Proxy synthesis: learning with synthetic classes for deep metric learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1460–1468 (2021)

    Google Scholar 

  17. Guo, X., Gao, L., Liu, X., Yin, J.: Improved deep embedded clustering with local structure preservation. In: International Joint Conference on Artificial Intelligence, pp. 1753–1759 (2017)

    Google Scholar 

  18. Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735–1742. IEEE (2006)

    Google Scholar 

  19. 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 

  20. Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)

  21. Hoi, S.C., Liu, W., Chang, S.F.: Semi-supervised distance metric learning for collaborative image retrieval and clustering. ACM Trans. Multimed. Comput. Commun. Appl. 6(3), 1–26 (2010)

    Article  Google Scholar 

  22. Hu, J., Lu, J., Tan, Y.P.: Discriminative deep metric learning for face verification in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1875–1882 (2014)

    Google Scholar 

  23. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)

    Google Scholar 

  24. Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117–128 (2010)

    Article  Google Scholar 

  25. Kim, S., Kim, D., Cho, M., Kwak, S.: Proxy anchor loss for deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3238–3247 (2020)

    Google Scholar 

  26. Kim, S., Seo, M., Laptev, I., Cho, M., Kwak, S.: Deep metric learning beyond binary supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2288–2297 (2019)

    Google Scholar 

  27. Kim, W., Goyal, B., Chawla, K., Lee, J., Kwon, K.: Attention-based ensemble for deep metric learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 760–777. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_45

    Chapter  Google Scholar 

  28. Ko, B., Gu, G.: Embedding expansion: augmentation in embedding space for deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7255–7264 (2020)

    Google Scholar 

  29. Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554–561 (2013)

    Google Scholar 

  30. Li, S., Chen, D., Liu, B., Yu, N., Zhao, R.: Memory-based neighbourhood embedding for visual recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6102–6111 (2019)

    Google Scholar 

  31. Lin, X., Duan, Y., Dong, Q., Lu, J., Zhou, J.: Deep variational metric learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 714–729. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_42

    Chapter  Google Scholar 

  32. Liu, L., Cao, J., Liu, M., Guo, Y., Chen, Q., Tan, M.: Dynamic extension nets for few-shot semantic segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1441–1449 (2020)

    Google Scholar 

  33. Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220 (2017)

    Google Scholar 

  34. Mikolov, T., Yih, W.T., Zweig, G.: Linguistic regularities in continuous space word representations. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 746–751 (2013)

    Google Scholar 

  35. Milbich, T., et al.: DiVA: diverse visual feature aggregation for deep metric learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 590–607. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_35

    Chapter  Google Scholar 

  36. Movshovitz-Attias, Y., Toshev, A., Leung, T.K., Ioffe, S., Singh, S.: No fuss distance metric learning using proxies. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 360–368 (2017)

    Google Scholar 

  37. Musgrave, K., Belongie, S., Lim, S.-N.: A metric learning reality check. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 681–699. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58595-2_41

    Chapter  Google Scholar 

  38. Oh Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4004–4012 (2016)

    Google Scholar 

  39. Opitz, M., Waltner, G., Possegger, H., Bischof, H.: Deep metric learning with BIER: boosting independent embeddings robustly. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 276–290 (2018)

    Article  Google Scholar 

  40. Qian, Q., Shang, L., Sun, B., Hu, J., Li, H., Jin, R.: SoftTriple Loss: deep metric learning without triplet sampling. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6450–6458 (2019)

    Google Scholar 

  41. Roth, K., Milbich, T., Sinha, S., Gupta, P., Ommer, B., Cohen, J.P.: Revisiting training strategies and generalization performance in deep metric learning. In: International Conference on Machine Learning, pp. 8242–8252. PMLR (2020)

    Google Scholar 

  42. Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)

    Google Scholar 

  43. Schütze, H., Manning, C.D., Raghavan, P.: Introduction to Information Retrieval, vol. 39. Cambridge University Press, Cambridge (2008)

    MATH  Google Scholar 

  44. Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)

    Article  Google Scholar 

  45. Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 1857–1865 (2016)

    Google Scholar 

  46. Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)

    Google Scholar 

  47. Teh, E.W., DeVries, T., Taylor, G.W.: ProxyNCA++: revisiting and revitalizing proxy neighborhood component analysis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 448–464. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58586-0_27

    Chapter  Google Scholar 

  48. Ustinova, E., Lempitsky, V.: Learning deep embeddings with histogram loss. In: Proceedings of the International Conference on Neural Information Processing Systems, pp. 4177–4185 (2016)

    Google Scholar 

  49. Volpi, R., Morerio, P., Savarese, S., Murino, V.: Adversarial feature augmentation for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5495–5504 (2018)

    Google Scholar 

  50. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)

    Google Scholar 

  51. Wang, J., et al.: Learning fine-grained image similarity with deep ranking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1386–1393 (2014)

    Google Scholar 

  52. Wang, X., Hua, Y., Kodirov, E., Hu, G., Garnier, R., Robertson, N.M.: Ranked list loss for deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5207–5216 (2019)

    Google Scholar 

  53. Wang, X., Han, X., Huang, W., Dong, D., Scott, M.R.: Multi-similarity loss with general pair weighting for deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5022–5030 (2019)

    Google Scholar 

  54. Wang, X., Zhang, H., Huang, W., Scott, M.R.: Cross-batch memory for embedding learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6388–6397 (2020)

    Google Scholar 

  55. Wang, Y., Pan, X., Song, S., Zhang, H., Huang, G., Wu, C.: Implicit semantic data augmentation for deep networks. In: Advances in Neural Information Processing Systems, vol. 32, pp. 12635–12644 (2019)

    Google Scholar 

  56. Wu, C.Y., Manmatha, R., Smola, A.J., Krahenbuhl, P.: Sampling matters in deep embedding learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2840–2848 (2017)

    Google Scholar 

  57. Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Feature transfer learning for face recognition with under-represented data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5704–5713 (2019)

    Google Scholar 

  58. Yu, B., Tao, D.: Deep metric learning with tuplet margin loss. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6490–6499 (2019)

    Google Scholar 

  59. Yuan, Y., Yang, K., Zhang, C.: Hard-aware deeply cascaded embedding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 814–823 (2017)

    Google Scholar 

  60. Zhai, A., Wu, H.Y.: Classification is a strong baseline for deep metric learning (2019)

    Google Scholar 

  61. Zhang, D., Li, Y., Zhang, Z.: Deep metric learning with spherical embedding. In: Advances in Neural Information Processing Systems, vol. 33, pp. 18772–18783 (2020)

    Google Scholar 

  62. Zhao, Y., Jin, Z., Qi, G., Lu, H., Hua, X.: An adversarial approach to hard triplet generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 508–524. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_31

    Chapter  Google Scholar 

  63. Zheng, W., Lu, J., Zhou, J.: Hardness-aware deep metric learning. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 3214–3228 (2021)

    Article  Google Scholar 

  64. Zheng, W., Chen, Z., Lu, J., Zhou, J.: Hardness-aware deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 72–81 (2019)

    Google Scholar 

  65. Zheng, W., Wang, C., Lu, J., Zhou, J.: Deep compositional metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9320–9329 (2021)

    Google Scholar 

  66. Zheng, W., Zhang, B., Lu, J., Zhou, J.: Deep relational metric learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12065–12074 (2021)

    Google Scholar 

  67. Zhu, Y., Yang, M., Deng, C., Liu, W.: Fewer is more: a deep graph metric learning perspective using fewer proxies. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17792–17803 (2020)

    Google Scholar 

Download references

Acknowledgements

This work was partially supported by Peng Cheng Laboratory Research Project No. PCL2021A07, National Natural Science Foundation of China (NSFC) 62072190, Program for Guangdong Introducing Innovative and Enterpreneurial Teams 2017ZT07X183.

Author information

Authors and Affiliations

  1. South China University of Technology, Guangzhou, China

    Lizhao Liu, Shangxin Huang, Zhuangwei Zhuang, Ran Yang & Mingkui Tan

  2. PengCheng Laboratory, Shenzhen, China

    Lizhao Liu & Yaowei Wang

  3. Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, Guangzhou, China

    Mingkui Tan

Authors
  1. Lizhao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shangxin Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhuangwei Zhuang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ran Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mingkui Tan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yaowei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Mingkui Tan or Yaowei 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 9926 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

Liu, L., Huang, S., Zhuang, Z., Yang, R., Tan, M., Wang, Y. (2022). DAS: Densely-Anchored Sampling for Deep Metric Learning. 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 13686. Springer, Cham. https://doi.org/10.1007/978-3-031-19809-0_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19809-0_23

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19808-3

  • Online ISBN: 978-3-031-19809-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation