Abstract
Deep Metric Learning (DML) methods automatically extract features from data and learn a non-linear transformation from the input to a semantically embedding space. Many DML methods focused to enhance the discrimination power of the learned metric by proposing novel sampling strategies or loss functions. This approach is very helpful when both the training and test examples are selected from the same set of categories. However, it is less effective in many applications of DML such as image retrieval and person-reidentification. Here, the DML should learn general semantic concepts from observed classes and employ them to rank or identify objects from unseen categories. Neglecting the generalization ability of the learned representation and just emphasizing to learn a more discriminative embedding on the observed classes may lead to the overfitting problem. To address this limitation, we propose a framework to enhance the generalization power of existing DML methods in a Zero-Shot Learning (ZSL) setting by general yet discriminative representation learning and employing a class adversarial neural network. To learn a general representation, we employ feature maps of intermediate layers in a deep neural network and enhance their discrimination power through an attention mechanism. Besides, a class adversarial network is utilized to force the deep model to seek class invariant features. We evaluate our work on widely used machine vision datasets in a ZSL setting. Extensive experimental results confirm that our framework can improve the generalization of existing DML methods, and it consistently outperforms baseline DML algorithms on unseen classes.
Similar content being viewed by others
Notes
Content-Based Information Retrieval
Zero-Shot Learning
Few-Shot Learning
Normalized Mutual Information
Deep Adversarial Metric Learning
downloaded from: https://github.com/dichotomies/proxy-nca
Adaptive Adversarial Deep Metric Learning
Source code: https://github.com/tomp11/metric_learning
Source code: https://github.com/dichotomies/proxy-nca
Normalized Mutual Information
General Discriminative Feature Learning
References
Chopra S, et al. (2005) Learning a similarity metric discriminatively, with application to face verification. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), IEEE
Hoffer E, Ailon N (2015). Deep metric learning using triplet network. International Workshop on Similarity-Based Pattern Recognition, Springer
Wang J, et al. (2014) Learning fine-grained image similarity with deep ranking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Ni J, et al. (2017) Fine-grained patient similarity measuring using deep metric learning. Proceedings of the 2017 ACM on conference on information and knowledge management
Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. Advances in Neural Information Processing Systems
Kaya M, Bilge HŞ (2019) Deep metric learning: a survey. Symmetry 11(9):1066
Simo-Serra E, et al. (2015) Discriminative learning of deep convolutional feature point descriptors. Proceedings of the IEEE International Conference on Computer Vision
Schroff F, et al. (2015) Facenet: a unified embedding for face recognition and clustering. Proceedings of the IEEE conference on computer vision and pattern recognition
Wah C, et al. (2011) The Caltech-UCSD Birds-200-2011 dataset, Computation & Neural Systems, technical report, CNS-TR-2011-001
Wu C-Y, et al. (2017) Sampling matters in deep embedding learning. Proceedings of the IEEE International Conference on Computer Vision
Zheng W, et al. (2019) Hardness-aware deep metric learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Kim M, et al. (2022) Variational continual proxy-anchor for deep metric learning. International Conference on Artificial Intelligence and Statistics, PMLR
Movshovitz-Attias Y, et al. (2017) No fuss distance metric learning using proxies. Proceedings of the IEEE International Conference on Computer Vision
Oh Song H, et al. (2017) Deep metric learning via facility location. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Qian Q, et al. (2019) Softtriple loss: deep metric learning without triplet sampling. Proceedings of the IEEE International Conference on Computer Vision
Ge W (2018) Deep metric learning with hierarchical triplet loss. Proceedings of the European conference on computer vision (ECCV)
Wang J, et al. (2017) Deep metric learning with angular loss. Proceedings of the IEEE International Conference on Computer Vision
Ustinova E, Lempitsky V (2016) Learning deep embeddings with histogram loss. Adv Neural Inf Proces Syst 29:4170–4178
Wang X, et al. (2019) Multi-similarity loss with general pair weighting for deep metric learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Yao H, Zhang S, Hong R, Zhang Y, Xu C, Tian Q (2019) Deep representation learning with part loss for person re-identification. IEEE Trans Image Process 28(6):2860–2871
Oh Song H, et al. (2016) Deep metric learning via lifted structured feature embedding. Proceedings of the IEEE conference on computer vision and pattern recognition
Jiang W, Huang K, Geng J, Deng X (2020) Multi-scale metric learning for few-shot learning. IEEE Trans Circ Syst Video Technol 31:1091–1102
Li X, Yu L, Fu CW, Fang M, Heng PA (2020) Revisiting metric learning for few-shot image classification. Neurocomputing 406:49–58
Duan Y, et al. (2018) Deep adversarial metric learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Wang Z, et al. (2020) Adaptive margin based deep adversarial metric learning. 2020 IEEE 6th Intl conference on big data security on cloud (BigDataSecurity), IEEE Intl conference on high performance and smart computing,(HPSC) and IEEE Intl conference on intelligent data and security (IDS), IEEE
Xu X, He L, Lu H, Gao L, Ji Y (2019) Deep adversarial metric learning for cross-modal retrieval. World Wide Web 22(2):657–672
Gu G, Ko B (2021) Proxy synthesis: learning with synthetic classes for deep metric learning. Proc AAAI Conference on Artificial Intelligence (AAAI), 34, 10853, 10860
Zhang H et al (2017) mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412
Chen B, Deng W (2019) Energy confused adversarial metric learning for zero-shot image retrieval and clustering. Proceedings of the AAAI Conference on Artificial Intelligence.
Zhu J, Zhong D, Luo K (2020) Boosting unconstrained Palmprint recognition with adversarial metric learning. IEEE Trans Biom Behav Identity Sci 2(4):388–398
Shen T, et al. (2018) Disan: directional self-attention network for rnn/cnn-free language understanding. Proceedings of the AAAI Conference on Artificial Intelligence
Szegedy C, et al. (2016) Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition
Krause J, et al. (2013) 3d object representations for fine-grained categorization. Proceedings of the IEEE International Conference on Computer Vision Workshops
Nilsback M-E, Zisserman A (2008). Automated flower classification over a large number of classes. 2008 Sixth Indian conference on computer vision, Graphics & Image Processing, IEEE
Acknowledgments
We would like to acknowledge the Machine Learning Lab in the Engineering Faculty of FUM for their kind and technical support.
Availability of data
Datasets used in the experiments are publicly available and can be downloaded from the following links:
1. Oxford 102 Flowers: https://www.robots.ox.ac.uk/~vgg/data/flowers/102/
2. CUB-200-2011: https://github.com/cyizhuo/CUB-200-2011-dataset
3. CARS-196: https://ai.stanford.edu/~jkrause/cars/car_dataset.html
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Al-Kaabi, K., Monsefi, R. & Zabihzadeh, D. A framework to enhance generalization of deep metric learning methods using general discriminative feature learning and class adversarial neural networks. Appl Intell 53, 8693–8711 (2023). https://doi.org/10.1007/s10489-022-03959-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03959-6