Advertisement

Unifying Deep Local and Global Features for Image Search

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12365)

Abstract

Image retrieval is the problem of searching an image database for items that are similar to a query image. To address this task, two main types of image representations have been studied: global and local image features. In this work, our key contribution is to unify global and local features into a single deep model, enabling accurate retrieval with efficient feature extraction. We refer to the new model as DELG, standing for DEep Local and Global features. We leverage lessons from recent feature learning work and propose a model that combines generalized mean pooling for global features and attentive selection for local features. The entire network can be learned end-to-end by carefully balancing the gradient flow between two heads – requiring only image-level labels. We also introduce an autoencoder-based dimensionality reduction technique for local features, which is integrated into the model, improving training efficiency and matching performance. Comprehensive experiments show that our model achieves state-of-the-art image retrieval on the Revisited Oxford and Paris datasets, and state-of-the-art single-model instance-level recognition on the Google Landmarks dataset v2. Code and models are available at https://github.com/tensorflow/models/tree/master/research/delf.

Keywords

Deep features Image retrieval Unified model 

Supplementary material

504476_1_En_43_MOESM1_ESM.pdf (7.3 mb)
Supplementary material 1 (pdf 7485 KB)

References

  1. 1.
    Arandjelović, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the CVPR (2016)Google Scholar
  2. 2.
    Araujo, A., Norris, W., Sim, J.: Computing receptive fields of convolutional neural networks. Distill (2019). https://distill.pub/2019/computing-receptive-fields
  3. 3.
    Avrithis, Y., Tolias, G.: Hough pyramid matching: speeded-up geometry re-ranking for large scale image retrieval. Int. J. Comput. Vision 107(1), 1–19 (2013).  https://doi.org/10.1007/s11263-013-0659-3CrossRefGoogle Scholar
  4. 4.
    Babenko, A., Lempitsky, V.: Aggregating local deep features for image retrieval. In: Proceedings of the ICCV (2015)Google Scholar
  5. 5.
    Babenko, A., Slesarev, A., Chigorin, A., Lempitsky, V.: Neural codes for image retrieval. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 584–599. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10590-1_38CrossRefGoogle Scholar
  6. 6.
    Barroso-Laguna, A., Riba, E., Ponsa, D., Mikolajczyk, K.: Key.Net: keypoint detection by handcrafted and learned CNN filters. In: Proceedings of the ICCV (2019)Google Scholar
  7. 7.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). CVIU 110(3), 346–359 (2008)Google Scholar
  8. 8.
    Chang, C., Yu, G., Liu, C., Volkovs, M.: Explore-exploit graph traversal for image retrieval. In: Proceedings of the CVPR (2019)Google Scholar
  9. 9.
    Chopra, S., Hadsell, R., LeCun, Y.: Learning a dimilarity metric discriminatively, with application to face verification. In: Proceedings of the CVPR (2005)Google Scholar
  10. 10.
    Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automatic query expansion with a generative feature model for object retrieval. In: Proceedings of the ICCV (2007)Google Scholar
  11. 11.
    Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the CVPR (2019)Google Scholar
  12. 12.
    DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: Proceedings of the CVPR Workshops (2018)Google Scholar
  13. 13.
    Dugas, C., Bengio, Y., Nadeau, C., Garcia, R.: Incorporating second-order functional knowledge for better option pricing. In: Proceedings of the NIPS (2001)Google Scholar
  14. 14.
    Dusmanu, M., et al.: D2-Net: a trainable CNN for joint detection and description of local features. In: Proceedings of the CVPR (2019)Google Scholar
  15. 15.
    Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Gordo, A., Almazán, J., Revaud, J., Larlus, D.: Deep image retrieval: learning global representations for image search. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 241–257. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_15CrossRefGoogle Scholar
  17. 17.
    Gordo, A., Almazán, J., Revaud, J., Larlus, D.: End-to-end learning of deep visual representations for image retrieval. Int. J. Comput. Vision 124(2), 237–254 (2017).  https://doi.org/10.1007/s11263-017-1016-8MathSciNetCrossRefGoogle Scholar
  18. 18.
    Gordo, A., Rodriguez-Serrano, J.A., Perronin, F., Valveny, E.: Leveraging category-level labels for instance-level image retrieval. In: Proceedings of the CVPR (2012)Google Scholar
  19. 19.
    He, K., Lu, Y., Sclaroff, S.: Local descriptors optimized for average precision. In: Proceedings of the CVPR (2018)Google Scholar
  20. 20.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR (2016)Google Scholar
  21. 21.
    Hinton, G.: Connectionist learning procedures. Artif. Intell. 40(1–3), 185–234 (1989)CrossRefGoogle Scholar
  22. 22.
    Iscen, A., Tolias, G., Avrithis, Y., Furon, T., Chum, O.: Efficient diffusion on region manifolds: recovering small objects with compact CNN representations. In: Proceedings of the CVPR (2017)Google Scholar
  23. 23.
    Jégou, H., Chum, O.: Negative evidences and co-occurences in image retrieval: the benefit of PCA and whitening. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7573, pp. 774–787. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33709-3_55CrossRefGoogle Scholar
  24. 24.
    Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 304–317. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-88682-2_24CrossRefGoogle Scholar
  25. 25.
    Jégou, H., Douze, M., Schmidt, C., Perez, P.: Aggregating local descriptors into a compact image representation. In: Proceedings of the CVPR (2010)Google Scholar
  26. 26.
    Jégou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., Schmid, C.: Aggregating local image descriptors into compact codes. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1704–1716 (2012)CrossRefGoogle Scholar
  27. 27.
    Jegou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: Proceedings of the CVPR (2014)Google Scholar
  28. 28.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91–110 (2004).  https://doi.org/10.1023/B:VISI.0000029664.99615.94CrossRefGoogle Scholar
  29. 29.
    Luo, Z., et al.: ContextDesc: local descriptor augmentation with cross-modality context. In: Proceedings of the CVPR (2019)Google Scholar
  30. 30.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. Image Vis. Comput. 22(10), 761–767 (2004)CrossRefGoogle Scholar
  31. 31.
    Mikolajczyk, K., Matas, J.: Improving descriptors for fast tree matching by optimal linear projection. In: Proceedings of the ICCV (2007)Google Scholar
  32. 32.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-47969-4_9CrossRefGoogle Scholar
  33. 33.
    Mishchuk, A., Mishkin, D., Radenovic, F., Matas, J.: Working hard to know your neighbor’s margins: local descriptor learning loss. In: Proceedings of the NIPS (2017)Google Scholar
  34. 34.
    Mishkin, D., Radenović, F., Matas, J.: Repeatability is not enough: learning affine regions via discriminability. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 287–304. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01240-3_18CrossRefGoogle Scholar
  35. 35.
    Mukundan, A., Tolias, G., Bursuc, A., Jégou, H., Chum, O.: Understanding and improving kernel local descriptors. Int. J. Comput. Vision 127(11), 1723–1737 (2018).  https://doi.org/10.1007/s11263-018-1137-8CrossRefGoogle Scholar
  36. 36.
    Mukundan, A., Tolias, G., Chum, O.: Explicit spatial encoding for deep local descriptors. In: Proceedings of the CVPR (2019)Google Scholar
  37. 37.
    Ng, T., Balntas, V., Tian, Y., Mikolajczyk, K.: SOLAR: second-order loss and attention for image retrieval. In: Proceedings of the ECCV (2020)Google Scholar
  38. 38.
    Nistér, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: Proceedings of the CVPR (2006)Google Scholar
  39. 39.
    Noh, H., Araujo, A., Sim, J., Weyand, T., Han, B.: Large-scale image retrieval with attentive deep local features. In: Proceedings of the ICCV (2017)Google Scholar
  40. 40.
    Obdrzalek, S., Matas, J.: Sub-linear indexing for large scale object recognition. In: Proceedings of the BMVC (2005)Google Scholar
  41. 41.
    Ono, Y., Trulls, E., Fua, P., Yi, K.M.: LF-Net: learning local features from images. In: Proceedings of the NIPS (2018)Google Scholar
  42. 42.
    Ozaki, K., Yokoo, S.: Large-scale landmark retrieval/recognition under a noisy and diverse dataset. arXiv:1906.04087 (2019)
  43. 43.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of the CVPR (2007)Google Scholar
  44. 44.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: improving particular object retrieval in large scale image databases. In: Proceedings of the CVPR (2008)Google Scholar
  45. 45.
    Radenović, F., Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Revisiting Oxford and Paris: large-scale image retrieval benchmarking. In: Proceedings of the CVPR (2018)Google Scholar
  46. 46.
    Radenović, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655–1668 (2018)CrossRefGoogle Scholar
  47. 47.
    Revaud, J., Almazan, J., de Rezende, R.S., de Souza, C.R.: Learning with average precision: training image retrieval with a listwise loss. In: Proceedings of the ICCV (2019)Google Scholar
  48. 48.
    Revaud, J., Souze, C.D., Weinzaepfel, P., Humenberger, M.: R2D2: repeatable and reliable detector and descriptor. In: Proceedings of the NeurIPS (2019)Google Scholar
  49. 49.
    Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: Proceedings of the CVPR (2019)Google Scholar
  50. 50.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the CVPR (2015)Google Scholar
  51. 51.
    Silberman, N., Guadarrama, S.: TensorFlow-Slim Image Classification Model Library (2016). https://github.com/tensorflow/models/tree/master/research/slim
  52. 52.
    Simeoni, O., Avrithis, Y., Chum, O.: Local features and visual words emerge in activations. In: Proceedings of the CVPR (2019)Google Scholar
  53. 53.
    Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: Proceedings of the ICCV (2003)Google Scholar
  54. 54.
    Taira, H., et al.: InLoc: indoor visual localization with dense matching and view synthesis. In: Proceedings of the CVPR (2018)Google Scholar
  55. 55.
    Teichmann, M., Araujo, A., Zhu, M., Sim, J.: Detect-to-retrieve: efficient regional aggregation for image search. In: Proceedings of the CVPR (2019)Google Scholar
  56. 56.
    Tian, Y., Yu, X., Fan, B., Wu, F., Heijnen, H., Balntas, V.: SOSNet: second order similarity regularization for local descriptor learning. In: Proceedings of the CVPR (2019)Google Scholar
  57. 57.
    Tolias, G., Avrithis, Y., Jégou, H.: Image search with selective match kernels: aggregation across single and multiple images. Int. J. Comput. Vis. 116, 247–261 (2016).  https://doi.org/10.1007/s11263-015-0810-4MathSciNetCrossRefGoogle Scholar
  58. 58.
    Tolias, G., Sicre, R., Jégou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: Proceeedings of the ICLR (2015)Google Scholar
  59. 59.
    Wang, F., Xiang, X., Cheng, J., Yuille, A.: NormFace: L2 hypersphere embedding for face verification. In: Proceedings of the ACM MM (2017)Google Scholar
  60. 60.
    Wang, H., et al.: CosFace: large margin cosine loss for deep dace recognition. In: Proceedings of the CVPR (2018)Google Scholar
  61. 61.
    Weyand, T., Araujo, A., Cao, B., Sim, J.: Google landmarks dataset v2 - a large-scale benchmark for instance-level recognition and retrieval. In: Proceedings of the CVPR (2020)Google Scholar
  62. 62.
    Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467–483. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_28CrossRefGoogle Scholar
  63. 63.
    Yokoo, S., Ozaki, K., Simo-Serra, E., Iizuka, S.: Two-stage discriminative re-ranking for large-scale landmark retrieval. In: Proceedings of the CVPR Workshops (2020)Google Scholar
  64. 64.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10590-1_53CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Google ResearchMountain ViewUSA

Personalised recommendations