Skip to main content
SpringerLink
Log in

Time-rEversed DiffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13680))

Included in the following conference series:

Abstract

In this paper, we tackle the challenging problem of Few-shot Object Detection. Existing FSOD pipelines (i) use average-pooled representations that result in information loss; and/or (ii) discard position information that can help detect object instances. Consequently, such pipelines are sensitive to large intra-class appearance and geometric variations between support and query images. To address these drawbacks, we propose a Time-rEversed diffusioN tEnsor Transformer (TENET), which i) forms high-order tensor representations that capture multi-way feature occurrences that are highly discriminative, and ii) uses a transformer that dynamically extracts correlations between the query image and the entire support set, instead of a single average-pooled support embedding. We also propose a Transformer Relation Head (TRH), equipped with higher-order representations, which encodes correlations between query regions and the entire support set, while being sensitive to the positional variability of object instances. Our model achieves state-of-the-art results on PASCAL VOC, FSOD, and COCO.

SZ was mainly in charge of the pipeline/developing the transformer. PK (corresponding author) was mainly in charge of mathematical design of TENET & TSO.

Code: https://github.com/ZS123-lang/TENET.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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.

    For \(r\!=\!2\), Eq. (12) yields \(\text {Diag}(\boldsymbol{\mathbb {I}}\!-\!(\boldsymbol{\mathbb {I}}\!-\!\boldsymbol{M})^{\eta _2})\). \(\text {Diag}(\text {Sqrtm}(\boldsymbol{M}))\) is its approximation.

References

  1. Exponentiation by squaring. Wikipedia. https://en.wikipedia.org/wiki/Exponentiation_by_squaring. Accessed 12 Mar 2021

  2. Tsallis entropy. Wikipedia. https://en.wikipedia.org/wiki/Tsallis_entropy. Accessed 12 Mar 2021

  3. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  4. Chen, H., Wang, Y., Wang, G., Qiao, Y.: LSTD: a low-shot transfer detector for object detection. In: McIlraith, S.A., Weinberger, K.Q. (eds.) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2–7 February 2018, pp. 2836–2843. AAAI Press (2018)

    Google Scholar 

  5. Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20–25 June 2009, Miami, Florida, USA, pp. 248–255. IEEE Computer Society (2009). https://doi.org/10.1109/CVPR.2009.5206848

  6. Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4

    Article  Google Scholar 

  7. Fan, Q., Zhuo, W., Tai, Y.: Few-shot object detection with attention-rpn and multi-relation detector. CoRR abs/1908.01998 (2019)

    Google Scholar 

  8. Girshick, R.B.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7–13 December 2015, pp. 1440–1448. IEEE Computer Society (2015). https://doi.org/10.1109/ICCV.2015.169

  9. Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: ICCV 2019, pp. 3463–3472. IEEE (2019). https://doi.org/10.1109/ICCV.2019.00356

  10. Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011–2023 (2020). https://doi.org/10.1109/TPAMI.2019.2913372

    Article  Google Scholar 

  11. Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27–November 2, 2019, pp. 8419–8428. IEEE (2019). https://doi.org/10.1109/ICCV.2019.00851

  12. Karlinsky, L., et al.: Repmet: representative-based metric learning for classification and few-shot object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 5197–5206. Computer Vision Foundation/IEEE (2019). https://doi.org/10.1109/CVPR.2019.00534

  13. Kong, T., Yao, A., Chen, Y., Sun, F.: Hypernet: towards accurate region proposal generation and joint object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 845–853. IEEE Computer Society (2016). https://doi.org/10.1109/CVPR.2016.98

  14. Koniusz, P., Tas, Y., Porikli, F.: Domain adaptation by mixture of alignments of second-or higher-order scatter tensors. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 7139–7148. IEEE Computer Society (2017). https://doi.org/10.1109/CVPR.2017.755

  15. Koniusz, P., Wang, L., Cherian, A.: Tensor representations for action recognition. In: TPAMI (2020)

    Google Scholar 

  16. Koniusz, P., Yan, F., Gosselin, P.H., Mikolajczyk, K.: Higher-order occurrence pooling on mid-and low-level features: Visual concept detection. Tech, Report (2013)

    Google Scholar 

  17. Koniusz, P., Yan, F., Gosselin, P., Mikolajczyk, K.: Higher-order occurrence pooling for bags-of-words: visual concept detection. IEEE Trans. Pattern Anal. Mach. Intell. 39(2), 313–326 (2017). https://doi.org/10.1109/TPAMI.2016.2545667

    Article  Google Scholar 

  18. Koniusz, P., Zhang, H.: Power normalizations in fine-grained image, few-shot image and graph classification. In: TPAMI (2020)

    Google Scholar 

  19. Koniusz, P., Zhang, H., Porikli, F.: A deeper look at power normalizations. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 5774–5783. IEEE Computer Society (2018). https://doi.org/10.1109/CVPR.2018.00605

  20. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017). https://doi.org/10.1145/3065386

    Article  Google Scholar 

  21. Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21, 1253–1278 (2000)

    Article  MathSciNet  Google Scholar 

  22. Ledoit, O., Wolf, M.: Honey, i shrunk the sample covariance matrix. J. Portfolio Manage. 30(4), 110–119 (2004). https://doi.org/10.3905/jpm.2004.110

    Article  Google Scholar 

  23. Lee, H., Lee, M., Kwak, N.: Few-shot object detection by attending to per-sample-prototype. In: WACV, 2022, Waikoloa, HI, USA, 3–8 January 2022, pp. 1101–1110. IEEE (2022). https://doi.org/10.1109/WACV51458.2022.00117

  24. Li, A., Li, Z.: Transformation invariant few-shot object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3094–3102 (2021)

    Google Scholar 

  25. Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 510–519. Computer Vision Foundation/IEEE (2019). https://doi.org/10.1109/CVPR.2019.00060

  26. Li, Y., et al.: Few-shot object detection via classification refinement and distractor retreatment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15395–15403 (2021)

    Google Scholar 

  27. Lin, T., Dollár, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 936–944. IEEE Computer Society (2017). https://doi.org/10.1109/CVPR.2017.106

  28. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  29. Lu, J., et al.: SOFT: softmax-free transformer with linear complexity. CoRR abs/2110.11945 (2021)

    Google Scholar 

  30. Rahman, S., Wang, L., Sun, C., Zhou, L.: Redro: efficiently learning large-sized spd visual representation. In: European Conference on Computer Vision (2020)

    Google Scholar 

  31. Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 6517–6525. IEEE Computer Society (2017). https://doi.org/10.1109/CVPR.2017.690

  32. Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. CoRR abs/1804.02767 (2018)

    Google Scholar 

  33. Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 7–12 December 2015, Montreal, Quebec, Canada, pp. 91–99 (2015)

    Google Scholar 

  34. Smola, A.J., Kondor, R.: Kernels and regularization on graphs. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT-Kernel 2003. LNCS (LNAI), vol. 2777, pp. 144–158. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-45167-9_12

    Chapter  MATH  Google Scholar 

  35. Sun, B., Li, B., Cai, S., Yuan, Y., Zhang, C.: FSCE: few-shot object detection via contrastive proposal encoding. CoRR abs/2103.05950 (2021)

    Google Scholar 

  36. Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7–12 June 2015, pp. 1–9. IEEE Computer Society (2015). https://doi.org/10.1109/CVPR.2015.7298594

  37. Tuzel, O., Porikli, F., Meer, P.: Region covariance: a fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 589–600. Springer, Heidelberg (2006). https://doi.org/10.1007/11744047_45

    Chapter  Google Scholar 

  38. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 2017, pp. 5998–6008 (2017)

    Google Scholar 

  39. Wang, X., Huang, T.E., Gonzalez, J., Darrell, T., Yu, F.: Frustratingly simple few-shot object detection. In: ICML 2020. Proceedings of Machine Learning Research, vol. 119, pp. 9919–9928. PMLR (2020)

    Google Scholar 

  40. West, J., Venture, D., Warnick, S.: Spring research presentation: a theoretical foundation for inductive transfer. Brigham Young Univ. College Phys. Math. Sci. (2007). https://web.archive.org/web/20070801120743/http://cpms.byu.edu/springresearch/abstract-entry?id=861

  41. Woodworth, R.S., Thorndike, E.L.: The influence of improvement in one mental function upon the efficiency of other functions. Psychol. Rev. (I) 8(3), 247–261 (1901). https://doi.org/10.1037/h0074898

    Article  Google Scholar 

  42. Wu, A., Han, Y., Zhu, L., Yang, Y.: Universal-prototype enhancing for few-shot object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9567–9576, October 2021

    Google Scholar 

  43. Wu, J., Liu, S., Huang, D., Wang, Y.: Multi-scale positive sample refinement for few-shot object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 456–472. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_27

    Chapter  Google Scholar 

  44. Xie, S., Girshick, R.B., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 5987–5995. IEEE Computer Society (2017). https://doi.org/10.1109/CVPR.2017.634

  45. Yan, X., Chen, Z., Xu, A., Wang, X., Liang, X., Lin, L.: Meta R-CNN: towards general solver for instance-level low-shot learning. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27–November 2, 2019, pp. 9576–9585. IEEE (2019). https://doi.org/10.1109/ICCV.2019.00967

  46. Yang, Y., Wei, F., Shi, M., Li, G.: Restoring negative information in few-shot object detection. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6–12 December 2020, virtual (2020)

    Google Scholar 

  47. Zhang, H., Zhang, L., Qi, X., Li, H., Torr, P.H.S., Koniusz, P.: Few-shot action recognition with permutation-invariant attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 525–542. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_31

    Chapter  Google Scholar 

  48. Zhang, H., Koniusz, P.: Power normalizing second-order similarity network for few-shot learning. In: IEEE Winter Conference on Applications of Computer Vision, WACV 2019, Waikoloa Village, HI, USA, 7–11 January 2019, pp. 1185–1193. IEEE (2019). https://doi.org/10.1109/WACV.2019.00131

  49. Zhang, H., Koniusz, P., Jian, S., Li, H., Torr, P.H.S.: Rethinking class relations: absolute-relative supervised and unsupervised few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9432–9441, June 2021

    Google Scholar 

  50. Zhang, S., Luo, D., Wang, L., Koniusz, P.: Few-shot object detection by second-order pooling. In: Proceedings of the Asian Conference on Computer Vision (2020)

    Google Scholar 

  51. Zhang, S., Wang, L., Murray, N., Koniusz, P.: Kernelized few-shot object detection with efficient integral aggregation. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  52. Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR 2021. OpenReview.net (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Australian National University, Canberra, Australia

    Shan Zhang

  2. Meta AI, London, UK

    Naila Murray

  3. University of Wollongong, Wollongong, Australia

    Lei Wang

  4. Data61/CSIRO, Canberra, Australia

    Piotr Koniusz

Authors
  1. Shan Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Naila Murray
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Piotr Koniusz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Piotr Koniusz .

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 941 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

Zhang, S., Murray, N., Wang, L., Koniusz, P. (2022). Time-rEversed DiffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection. 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 13680. Springer, Cham. https://doi.org/10.1007/978-3-031-20044-1_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20044-1_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20043-4

  • Online ISBN: 978-3-031-20044-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation