Skip to main content
Springer Nature Link
Log in

Rove-Tree-11: The Not-so-Wild Rover a Hierarchically Structured Image Dataset for Deep Metric Learning Research

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13845))

Included in the following conference series:

  • 439 Accesses

Abstract

We present a new dataset of images of pinned insects from museum collections along with a ground truth phylogeny (a graph representing the relative evolutionary distance between species). The images include segmentations, and can be used for clustering and deep hierarchical metric learning. As far as we know, this is the first dataset released specifically for generating phylogenetic trees. We provide several benchmarks for deep metric learning using a selection of state-of-the-art methods.

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

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    To genus-level means that each species within a genus is considered unresolved, or equally likely to be related to any other species within that genus.

  2. 2.

    The taxonomy represents how the organism is classified - ie which class, order, family the organism belongs to, and is a non binary tree. The phylogeny represents how related different species are together, and would ideally be a binary tree. In an ideal world the taxonomy would be a congruent to the phylogeny, but in reality they tend to diverge as taxonomic revisions take longer.

  3. 3.

    it is, however, different from the edit distance popular in computer science.

References

  1. Bakalar, N.: Nicholas. The New York Times (2014). https://www.nytimes.com/2014/05/27/science/welcoming-the-newly-discovered.html

  2. Bameri, F., Pourreza, H.R., Taherinia, A.H., Aliabadian, M., Mortezapour, H.R., Abdilzadeh, R.: TMTCPT: The tree method based on the taxonomic categorization and the phylogenetic tree for fine-grained categorization. Biosystems 195, 104137 (2020). https://doi.org/10.1016/j.biosystems.2020.104137

  3. Brunke, A., Smetana, A.: A new genus of staphylinina and a review of major lineages (staphylinidae: Staphylininae: Staphylinini). System. Biodiv. 17, 745–758 (2019). https://doi.org/10.1080/14772000.2019.1691082

    Article  Google Scholar 

  4. Chani-Posse, M.R., Brunke, A.J., Chatzimanolis, S., Schillhammer, H., Solodovnikov, A.: Phylogeny of the hyper-diverse rove beetle subtribe philonthina with implications for classification of the tribe staphylinini (coleoptera: Staphylinidae). Cladistics 34(1), 1–40 (2018). https://doi.org/10.1111/cla.12188

    Article  Google Scholar 

  5. Cho, H., Ahn, C., Min Yoo, K., Seol, J., Lee, S.g.: Leveraging class hierarchy in fashion classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops (October 2019)

    Google Scholar 

  6. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference On Computer Vision And Pattern Recognitio, pp. 248–255. IEEE (2009)

    Google Scholar 

  7. Deng, J., Guo, J., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. CoRR abs/ arXiv: 1801.07698 (2018)

  8. DiSSCo: Distributed system of scientific collections (July 2022). https://www.dissco.eu/

  9. Felsenstein, J.: Evolutionary trees from DNA sequences: A maximum likelihood approach. J. Mol. Evol. 17, 368–376 (1981)

    Article  Google Scholar 

  10. Felsenstein, J.: Statistical inference of phylogenies. J. Royal Statis. Soc. Ser. A (General) 146(3), 246–262 (1983). https://doi.org/10.2307/2981654

    Article  MATH  Google Scholar 

  11. Felsenstein, J.: Inferring phylogenies. Sinauer associates, Sunderland, MA (2003)

    Google Scholar 

  12. Fink, M., Ullman, S.: From aardvark to zorro: A benchmark for mammal image classification. Int. J. Comput. Vision 77(1–3), 143–156 (2008). https://doi.org/10.1007/s11263-007-0066-8

    Article  Google Scholar 

  13. Goëau, H., Bonnet, P., Joly, A.: Overview of plantclef 2021: cross-domain plant identification. In: Working Notes of CLEF 2021-Conference and Labs of the Evaluation Forum, vol. 2936, pp. 1422–1436 (2021)

    Google Scholar 

  14. Gutschenreiter, D., Bech, S.: Deep-learning methods on taxonomic beetle data Automated segmentation and classification of beetles on genus and species level. Master’s thesis, University of Copenhagen (2021)

    Google Scholar 

  15. Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06). vol. 2, pp. 1735–1742 (2006). https://doi.org/10.1109/CVPR.2006.100

  16. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)

  17. Hedrick, B.P., et al.: Digitization and the future of natural history collections. Bioscience 70(3), 243–251 (2020). https://doi.org/10.1093/biosci/biz163

    Article  Google Scholar 

  18. Hudson, L.N., et al.: Inselect: Automating the digitization of natural history collections. PLoS ONE 10(11), 1–15 (2015). https://doi.org/10.1371/journal.pone.0143402

    Article  Google Scholar 

  19. Höhna, L., Heath, B., Lartillot, M., Huelsenbeck, R.: Revbayes: Bayesian phylogenetic inference using graphical models and an interactive model-specification language. Syst. Biol. 65, 726–736 (2016)

    Article  Google Scholar 

  20. iDigBio: Integrated digitized biocollections (July 2022). https://www.idigbio.org/

  21. J. Peraire, S.W.: Lecture notes from mit course 16.07 dynamics, fall 2008. l26–3d rigid body dynamics: The inertia tensor (2008). https://ocw.mit.edu/courses/16-07-dynamics-fall-2009/dd277ec654440f4c2b5b07d6c286c3fd_MIT16_07F09_Lec26.pdf

  22. Kaya, M., B\(\dot{i}\)lge, H.S.: Deep metric learning: A survey. Symmetry 11(9) (2019). https://doi.org/10.3390/sym11091066, https://www.mdpi.com/2073-8994/11/9/1066

  23. Kiel, S.: Assessing bivalve phylogeny using deep learning and computer vision approaches. bioRxiv (2021). https://doi.org/10.1101/2021.04.08.438943, https://www.biorxiv.org/content/early/2021/04/09/2021.04.08.438943

  24. Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia (2013)

    Google Scholar 

  25. Kuhner, M.K., Yamato, J.: Practical performance of tree comparison metrics. System. Biol. 64(2), 205–214 (2014). https://doi.org/10.1093/sysbio/syu085

    Article  Google Scholar 

  26. Lee, M., Palci, A.: Morphological phylogenetics in the genomic age. Current Biol. 25(19), R922–R929 (2015). https://doi.org/10.1016/j.cub.2015.07.009, https://www.sciencedirect.com/science/article/pii/S096098221500812X

  27. Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2016)

    Google Scholar 

  28. MacQueen, J.: Classification and analysis of multivariate observations. In: 5th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)

    Google Scholar 

  29. Movshovitz-Attias, Y., Toshev, A., Leung, T.K., Ioffe, S., Singh, S.: No fuss distance metric learning using proxies. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 360–368 (2017). https://doi.org/10.1109/ICCV.2017.47

  30. 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 

  31. Natural History Museum of Denmark: Digital nature: Giant grant makes the natural history collections of denmark accessible to everyone (2021). Newsletter

  32. Natural History Museum of Denmark: (2022). Entomology - Dry and Wet Collections. Homepage

  33. Nye, T., Lio, P., Gilks, W.: A novel algorithm and web-based tool for comparing two alternative phylogenetic trees. Bioinformatics (Oxford, England) 22, 117–119 (2006). https://doi.org/10.1093/bioinformatics/bti720

    Article  Google Scholar 

  34. Orlov, I., Leschen, R.A., Żyła, D., Solodovnikov, A.: Total-evidence backbone phylogeny of aleocharinae (coleoptera: Staphylinidae). Cladistics 37(4), 343–374 (2021). https://doi.org/10.1111/cla.12444

    Article  Google Scholar 

  35. Parins-Fukuchi, C.: Use of continuous traits can improve morphological phylogenetics. System. Biol. 67(2), 328–339 (2017). https://doi.org/10.1093/sysbio/syx072

    Article  Google Scholar 

  36. Popov, D., Roychoudhury, P., Hardy, H., Livermore, L., Norris, K.: The value of digitising natural history collections. Res. Ideas Outcomes 7, e78844 (2021). https://doi.org/10.3897/rio.7.e78844

  37. Robinson, D., Foulds, L.: Comparison of phylogenetic trees. Math. Biosci. 53(1), 131–147 (1981). https://doi.org/10.1016/0025-5564(81)90043-2, https://www.sciencedirect.com/science/article/pii/0025556481900432

  38. Roth, K., Milbich, T., Sinha, S., Gupta, P., Ommer, B., Cohen, J.P.: Revisiting training strategies and generalization performance in deep metric learning (2020)

    Google Scholar 

  39. Tan, M., Le, Q.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 6105–6114. PMLR (09–15 June 2019), https://proceedings.mlr.press/v97/tan19a.html

  40. Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., MacAodha, O.: Benchmarking representation learning for natural world image collections. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12884–12893 (2021)

    Google Scholar 

  41. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset. Tech. Rep. CNS-TR-2011-001, California Institute of Technology (2011)

    Google Scholar 

  42. Wang, X., Han, X., Huang, W., Dong, D., Scott, M.R.: Multi-similarity loss with general pair weighting for deep metric learning. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5017–5025 (2019). https://doi.org/10.1109/CVPR.2019.00516

  43. Wu, C.Y., Manmatha, R., Smola, A.J., Krähenbühl, P.: Sampling matters in deep embedding learning. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2859–2867 (2017). https://doi.org/10.1109/ICCV.2017.309

  44. Wu, X., Zhan, C., Lai, Y., Cheng, M.M., Yang, J.: Ip102: A large-scale benchmark dataset for insect pest recognition. In: IEEE CVPR, pp. 8787–8796 (2019)

    Google Scholar 

  45. Yuan, Y., Chen, W., Yang, Y., Wang, Z.: In defense of the triplet loss again: Learning robust person re-identification with fast approximated triplet loss and label distillation (2019)

    Google Scholar 

  46. Żyła, D., Bogri, A., Hansen, A.K., Jenkins Shaw, J., Kypke, J., Solodovnikov, A.: A New Termitophilous Genus of Paederinae Rove Beetles (Coleoptera, Staphylinidae) from the Neotropics and Its Phylogenetic Position. Neotrop. Entomol. 51(2), 282–291 (2022). https://doi.org/10.1007/s13744-022-00946-x

    Article  Google Scholar 

  47. Żyła, D., Solodovnikov, A.: Multilocus phylogeny defines a new classification of staphylininae (coleoptera, staphylinidae), a rove beetle group with high lineage diversity. Syst. Entomol. 45(1), 114–127 (2020). https://doi.org/10.1111/syen.12382

    Article  Google Scholar 

Download references

Acknowledgements

Many people have been involved in this project. First we would like to thank David Gutschenreiter, Søren Bech and André Fastrup who took the photos of the unit trays and completed the initial segmentations of the images as part of their theses. Next, we would like to thank Alexey Solodovnikov of the Natural History Museum of Denmark for providing the specimens, the ground truth phylogeny and guidance for all things entomological. Also, thanks Francois Lauze and the entire Phylorama team for their input the project.

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Copenhagen, Universitetsparken 1, 2100, Copenhagen, Denmark

    Roberta Hunt & Kim Steenstrup Pedersen

  2. Natural History Museum of Denmark, Øster Voldgade 5 - 7, 1350, Copenhagen, Denmark

    Kim Steenstrup Pedersen

Authors
  1. Roberta Hunt
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kim Steenstrup Pedersen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Roberta Hunt .

Editor information

Editors and Affiliations

  1. University of Wollongong, Wollongong, NSW, Australia

    Lei Wang

  2. University of Bonn, Bonn, Germany

    Juergen Gall

  3. University of Adelaide, Adelaide, SA, Australia

    Tat-Jun Chin

  4. National Institute of Informatics, Tokyo, Japan

    Imari Sato

  5. Johns Hopkins University, Baltimore, MD, USA

    Rama Chellappa

Ethics declarations

Ethical Concerns

Models similar to those described, if applied to images of faces, could be used to generate family trees for humans. This could result in public images being used to infer familial relationships which could have a negative societal impact. The authors strongly discourage this form of misuse of the proposed methods.

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 715 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Hunt, R., Pedersen, K.S. (2023). Rove-Tree-11: The Not-so-Wild Rover a Hierarchically Structured Image Dataset for Deep Metric Learning Research. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13845. Springer, Cham. https://doi.org/10.1007/978-3-031-26348-4_25

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-26348-4_25

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-26347-7

  • Online ISBN: 978-3-031-26348-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation