Understanding and Exploiting Dependent Variables with Deep Metric Learning

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.

[1]  Lin Wu,et al.  Deep adaptive feature embedding with local sample distributions for person re-identification , 2017, Pattern Recognit..

[2]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[3]  Andrei Boiarov,et al.  Large Scale Landmark Recognition via Deep Metric Learning , 2019, CIKM.

[4]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[5]  V. B. Surya Prasath,et al.  Effects of Distance Measure Choice on KNN Classifier Performance-A Review , 2019 .

[6]  Ambedkar Dukkipati,et al.  Generative Adversarial Residual Pairwise Networks for One Shot Learning , 2017, ArXiv.

[7]  Melvyn L. Smith,et al.  Towards on-farm pig face recognition using convolutional neural networks , 2018, Comput. Ind..

[8]  Jonathan Krause,et al.  3D Object Representations for Fine-Grained Categorization , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[9]  Raul Fonseca Neto,et al.  A Music Classification model based on metric learning applied to MP3 audio files , 2020, Expert Syst. Appl..

[10]  Eric P. Xing,et al.  Domain Adaption in One-Shot Learning , 2018, ECML/PKDD.

[11]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[12]  Kihyuk Sohn,et al.  Improved Deep Metric Learning with Multi-class N-pair Loss Objective , 2016, NIPS.

[13]  Bernhard Pfahringer,et al.  Fast Metric Learning For Deep Neural Networks , 2015 .

[14]  Arjan Durresi,et al.  A survey: Control plane scalability issues and approaches in Software-Defined Networking (SDN) , 2017, Comput. Networks.

[15]  Xudong Lin,et al.  Deep Adversarial Metric Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Shruti Mittal,et al.  Siamese Neural Networks for One-shot detection of Railway Track Switches , 2017, ArXiv.

[17]  Soubhik Sanyal.  Discriminative Descriptors for Unconstrained Face and Object Recognition , 2018 .

[18]  Kiyoharu Aizawa,et al.  Significance of Softmax-Based Features over Metric Learning-Based Features , 2017 .

[19]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, ICCV 2003.

[20]  Bharath Hariharan,et al.  Low-Shot Visual Recognition by Shrinking and Hallucinating Features , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[21]  Yu Zhang,et al.  A Survey on Multi-Task Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[22]  Daan Wierstra,et al.  One-shot Learning with Memory-Augmented Neural Networks , 2016, ArXiv.

[23]  Hugo Larochelle,et al.  Few-Shot Learning , 2020, Computer Vision.

[24]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Daejin Park,et al.  Accurate Age Estimation Using Multi-Task Siamese Network-Based Deep Metric Learning for Frontal Face Images , 2018, Symmetry.

[26]  Hang Li,et al.  Meta-SGD: Learning to Learn Quickly for Few Shot Learning , 2017, ArXiv.

[27]  Daniele Bonadiman,et al.  Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning , 2019, W-NUT@EMNLP.

[28]  Vijay S. Pande,et al.  Low Data Drug Discovery with One-Shot Learning , 2016, ACS central science.

[29]  Torsten Sattler,et al.  A Cross-Season Correspondence Dataset for Robust Semantic Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Nicu Sebe,et al.  Low-Shot Learning From Imaginary 3D Model , 2019, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

[31]  Yi Yang,et al.  Person Re-identification: Past, Present and Future , 2016, ArXiv.

[32]  Mohsen Guizani,et al.  Deep Learning for IoT Big Data and Streaming Analytics: A Survey , 2017, IEEE Communications Surveys & Tutorials.

[33]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[34]  Thomas Paine,et al.  Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions , 2017, ICLR.

[35]  Qiang Yang,et al.  An Overview of Multi-task Learning , 2018 .

[36]  Devraj Mandal,et al.  Aligned discriminative pose robust descriptors for face and object recognition , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[37]  Abhinav Gupta,et al.  Learning a Predictable and Generative Vector Representation for Objects , 2016, ECCV.

[38]  Chen Huang,et al.  Local Similarity-Aware Deep Feature Embedding , 2016, NIPS.

[39]  Zilei Wang,et al.  VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[40]  Xudong Lin,et al.  Deep Variational Metric Learning , 2018, ECCV.

[41]  Xiaogang Jin,et al.  Quadruplet Network With One-Shot Learning for Fast Visual Object Tracking , 2017, IEEE Transactions on Image Processing.

[42]  Kaiqi Huang,et al.  Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Bodo Rosenhahn,et al.  Triplet-Based Deep Similarity Learning for Person Re-Identification , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[45]  Fatih Murat Porikli,et al.  Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts , 2018, ACCV.

[46]  Ahmad B. A. Hassanat,et al.  Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: A Review , 2019, Big Data.

[47]  Padmanabhan Rajan,et al.  Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss , 2019, The Journal of the Acoustical Society of America.

[48]  Victor S. Lempitsky,et al.  Learning Deep Embeddings with Histogram Loss , 2016, NIPS.

[49]  Huibing Wang,et al.  Multi-feature distance metric learning for non-rigid 3D shape retrieval , 2019, Multimedia Tools and Applications.

[50]  Le Wang,et al.  Ladder Loss for Coherent Visual-Semantic Embedding , 2019, AAAI.

[51]  Tea Marasovic,et al.  Accelerometer based gesture recognition system using distance metric learning for nearest neighbour classification , 2012, 2012 IEEE International Workshop on Machine Learning for Signal Processing.