Abstract
Deep Metric Learning (DML) approaches learn to represent inputs to a lower-dimensional latent space such that the distance between representations in this space corresponds with a predefined notion of similarity. This paper investigates how the mapping element of DML may be exploited in situations where the salient features in arbitrary classification problems vary over time or due to changing underlying variables. Examples of such variable features include seasonal and time-of-day variations in outdoor scenes in place recognition tasks for autonomous navigation and age/gender variations in human/animal subjects in classification tasks for medical/ethological studies. Through the use of visualisation tools for observing the distribution of DML representations per each query variable for which prior information is available, the influence of each variable on the classification task may be better understood. Based on these relationships, prior information on these salient background variables may be exploited at the inference stage of the DML approach by using a clustering algorithm to improve classification performance. This research proposes such a methodology establishing the saliency of query background variables and formulating clustering algorithms for better separating latent-space representations at run-time. The paper also discusses online management strategies to preserve the quality and diversity of data and the representation of each class in the gallery of embeddings in the DML approach. We also discuss latent works towards understanding the relevance of underlying/multiple variables with DML.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sanyal, S.: Discriminative descriptors for unconstrained face and object recognition (2017)
Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification (2017)
Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future (2016)
Wang, H., Li, H., Peng, J., Fu, X.: Multi-feature distance metric learning for non-rigid 3D shape retrieval. Multimed. Tools Appl. 78, 30943–30958 (2019). https://doi.org/10.1007/s11042-019-7670-9
Boiarov, A., Tyantov, E.: Large scale landmark recognition via deep metric learning (2019). https://doi.org/10.1145/3357384.3357956
Bonadiman, D., Kumar, A., Mittal, A.: Large scale question paraphrase retrieval with smoothed deep metric learning (2019)
da Silva, A.C.M., Coelho, M.A.N., Neto, R.F.: A music classification model based on metric learning applied to MP3 audio files. Expert Syst. Appl. 144, 113071 (2020). https://doi.org/10.1016/j.eswa.2019.113071
Thakur, A., Thapar, D., Rajan, P., Nigam, A.: Deep metric learning for bioacoustic classification: Overcoming training data scarcity using dynamic triplet loss. J. Acoust. Soc. Am. 146, 534–547 (2019). https://doi.org/10.1121/1.5118245
Marasović, T., Papić, V.: Accelerometer based gesture recognition system using distance metric learning for nearest neighbour classification. In: IEEE International Workshop on Machine Learning for Signal Processing, MLSP (2012)
Jeong, Y., Lee, S., Park, D., Park, K.H.: SS symmetry accurate age estimation using multi-task siamese network-based deep metric learning for front face images (2018). https://doi.org/10.3390/sym10090385
Rahman, S., Khan, S., Porikli, F.: Zero-shot object detection: learning to simultaneously recognize and localize novel concepts (2018)
Altae-Tran, H., Ramsundar, B., Pappu, A.S., Pande, V.: Low data drug discovery with one-shot learning. ACS Cent. Sci. 3, 283–293 (2017). https://doi.org/10.1021/acscentsci.6b00367
Dong, N., Xing, E.P.: Domain adaption in one-shot learning (2018)
Rao, D.J., Mittal, S., Ritika, S.: Siamese neural networks for one-shot detection of railway track switches (2017)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: International Conference on Learning Representations, pp. 1–11 (2017)
Fei-Fei, Li, Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28, 594–611 (2006). https://doi.org/10.1109/TPAMI.2006.79
Fe-Fei, L., Fergus, R., Perona, P.: A Bayesian approach to unsupervised one-shot learning of object categories. In: Proceedings Ninth IEEE International Conference on Computer Vision, vol. 2, pp.1134–1141. IEEE (2003)
Reed, S., Chen, Y., Paine, T., et al.: Few-shot autoregressive density estimation: towards learning to learn distributions. arXiv Prepr arXiv:171010304 (2018)
Mehrotra, A., Dukkipati, A.: Generative adversarial residual pairwise networks for one shot learning (2017)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features (2016)
Pahde, F., Puscas, M., Wolff, J., et al.: Low-shot learning from imaginary 3D model (2019)
Santoro, A., Bartunov, S., Botvinick, M., et al.: One-shot learning with memory-augmented neural networks (2016)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-SGD: learning to learn quickly for few-shot learning (2017)
Hou, S., Feng, Y., Wang, Z.: VegFru: a domain-specific dataset for fine-grained visual categorization (2017)
(PDF) Attention for Fine-Grained Categorization. https://www.researchgate.net/publication/269933088_Attention_for_Fine-Grained_Categorization. Accessed 16 Jan 2020
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization (2016)
Hansen, M.F., Smith, M.L., Smith, L.N., et al.: Towards on-farm pig face recognition using convolutional neural networks. Comput. Ind. 98, 145–152 (2018). https://doi.org/10.1016/j.compind.2018.02.016
Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification (2018)
Liao, W., Yang, M.Y., Zhan, N., Rosenhahn, B.: Triplet-based deep similarity learning for person re-identification (2017)
Mohammadi, M., Al-Fuqaha, A., Sorour, S., Guizani, M.: Deep learning for IoT big data and streaming analytics: a survey (2017)
Gouk, H., Pfahringer, B., Cree, M.: Fast metric learning for deep neural networks (2016)
Surya Prasath, V.B., Alfeilat, H.A.A., Hassanat, A.B., et al.: Effects of distance measure choice on KNN classifier performance-a review (2019)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition (2015)
Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering (2015). https://doi.org/10.1109/cvpr.2015.7298682
Girdhar, R., Fouhey, D.F., Rodriguez, M., Gupta, A.: Learning a predictable and generative vector representation for objects. In: Lecture Notes on Computer Science (Including Subser Lecture Notes on Artificial Intelligence Lecture Notes on Bioinformatics). LNCS, vol. 9910 (2016).. https://doi.org/10.1007/978-3-319-46466-4_29
Horiguchi, S., Ikami, D., Aizawa, K.: Significance of softmax - based features over metric learning - based features. In: ICLR 2017 (2017)
Huang, C., Loy, C.C., Tang, X.: Local similarity-aware deep feature embedding (2016)
Ustinova, E., Lempitsky, V.: Learning deep embeddings with histogram loss (2016)
Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification (2016)
Dong, X., Shen, J., Wu, D., et al.: Quadruplet network with one-shot learning for fast visual object tracking (2019)
Sohn, K.: Improved deep metric learning with multi-class N-pair loss objective (2016)
Zhou, M., Niu, Z., Wang, L., et al.: Ladder loss for coherent visual-semantic embedding (2019)
Zhang, Y., Yang, Q.: A Survey on multi-task learning (2017)
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10, 207–244 (2009). https://doi.org/10.1145/1577069.1577078
Bonaccorso, G.: Machine Learning Algorithms Popular Algorithms for Data Science and Machine Learning, 2nd edn. Packt Publishing Ltd, Birmingham (2018)
Larsson, M., Stenborg, E., Hammarstrand, L., et al.: A cross-season correspondence dataset for robust semantic segmentation (2019)
Wu, L., Wang, Y., Gao, J., Li, X.: Deep adaptive feature embedding with local sample distributions for person re-identification (2017)
Lin, X., Duan, Y., Dong, Q., et al.: Deep variational metric learning (2019)
Acknowledgment
This work was supported, in part, by Science Foundation Ireland grant 13/RC/2094 and co-funded under the European Regional Development Fund through the Southern & Eastern Regional Operational Programme to Lero - the Irish Software Research Centre (www.lero.ie).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
O’Mahony, N. et al. (2021). Understanding and Exploiting Dependent Variables with Deep Metric Learning. In: Arai, K., Kapoor, S., Bhatia, R. (eds) Intelligent Systems and Applications. IntelliSys 2020. Advances in Intelligent Systems and Computing, vol 1250. Springer, Cham. https://doi.org/10.1007/978-3-030-55180-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-55180-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-55179-7
Online ISBN: 978-3-030-55180-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)