Deep Metric Learning: A Survey

Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.

Download Full-text

An approach to partial occlusion using deep metric learning

International Journal of Informatics and Communication Technology (IJ-ICT) ◽

10.11591/ijict.v10i3.pp204-211 ◽

2021 ◽

Vol 10 (3) ◽

pp. 204

Author(s):

Chethana Hadya Thammaiah ◽

Trisiladevi Chandrakant Nagavi

Keyword(s):

Euclidean Distance ◽

Metric Learning ◽

Partial Occlusion ◽

System A ◽

Learning Tasks ◽

Optimal Distance ◽

Biometric Systems ◽

In The Wild ◽

Deep Metric Learning ◽

Histogram Of Gradients

<span>The human face can be used as an identification and authentication tool in biometric systems. Face recognition in forensics is a challenging task due to the presence of partial occlusion features like wearing a hat, sunglasses, scarf, and beard. In forensics, criminal identification having partial occlusion features is the most difficult task to perform. In this paper, a combination of the histogram of gradients (HOG) with Euclidean distance is proposed. Deep metric learning is the process of measuring the similarity between the samples using optimal distance metrics for learning tasks. In the proposed system, a deep metric learning technique like HOG is used to generate a 128d real feature vector. Euclidean distance is then applied between the feature vectors and a tolerance threshold is set to decide whether it is a match or mismatch. Experiments are carried out on disguised faces in the wild (DFW) dataset collected from IIIT Delhi which consists of 1000 subjects in which 600 subjects were used for testing and the remaining 400 subjects were used for training purposes. The proposed system provides a recognition accuracy of 89.8% and it outperforms compared with other existing methods.</span>

Download Full-text

Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data

Remote Sensing ◽

10.3390/rs12101593 ◽

2020 ◽

Vol 12 (10) ◽

pp. 1593

Author(s):

Hongying Liu ◽

Ruyi Luo ◽

Fanhua Shang ◽

Xuechun Meng ◽

Shuiping Gou ◽

...

Keyword(s):

Real World ◽

Metric Learning ◽

Feature Learning ◽

Linear Mapping ◽

Layer By Layer ◽

Learning Networks ◽

Distance Metric ◽

Linear Projection ◽

Deep Metric Learning

Recently, classification methods based on deep learning have attained sound results for the classification of Polarimetric synthetic aperture radar (PolSAR) data. However, they generally require a great deal of labeled data to train their models, which limits their potential real-world applications. This paper proposes a novel semi-supervised deep metric learning network (SSDMLN) for feature learning and classification of PolSAR data. Inspired by distance metric learning, we construct a network, which transforms the linear mapping of metric learning into the non-linear projection in the layer-by-layer learning. With the prior knowledge of the sample categories, the network also learns a distance metric under which all pairs of similarly labeled samples are closer and dissimilar samples have larger relative distances. Moreover, we introduce a new manifold regularization to reduce the distance between neighboring samples since they are more likely to be homogeneous. The categorizing is achieved by using a simple classifier. Several experiments on both synthetic and real-world PolSAR data from different sensors are conducted and they demonstrate the effectiveness of SSDMLN with limited labeled samples, and SSDMLN is superior to state-of-the-art methods.

Download Full-text

Crispr2vec: Machine Learning Model Predicts Off-Target Cuts of CRISPR systems

10.1101/2020.10.28.359885 ◽

2020 ◽

Author(s):

Tara Basu Trivedi ◽

Ron Boger ◽

Govinda M. Kamath ◽

Georgios Evangelopoulos ◽

Jamie Cate ◽

...

Keyword(s):

Metric Learning ◽

Sampling Strategy ◽

Target Sequence ◽

Fixed Target ◽

Guide Rna ◽

Machine Learning Model ◽

Genetic Modifications ◽

Deep Metric Learning ◽

Target Effects

1AbstractClustered Regularly Interspaced Short Palindromic Repeats (CRISPR)/CRISPR-Cas systems have revolutionized gene editing, with applications in therapeutics, diagnostics, agriculture, and developing disease models. However, CRISPR-Cas suffers from off-target effects — unintended genetic modifications in the genome that arise from its use. In this work, we present crispr2vec: a deep metric learning approach for embedding CRISPR single guide RNA (sgRNA) sequences and predicting off-target cuts. Given a fixed target sequence, we show that our learned embedding yields a faithful representation of potential off-targets. We present a new triplet sampling strategy specifically for CRISPR sequences that improves the quality of our embedding. We show the resulting embedding generalizes across different off-target cut detection assays. Finally, we demonstrate the superiority of our deep metric learning method in its ability to predict off-target cuts compared to previous literature in cross fold validation across different datasets for both seen and unseen sgRNAs.

Download Full-text

Compressed Self-Attention for Deep Metric Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5762 ◽

2020 ◽

Vol 34 (04) ◽

pp. 3561-3568

Author(s):

Ziye Chen ◽

Mingming Gong ◽

Yanwu Xu ◽

Chaohui Wang ◽

Kun Zhang ◽

...

Keyword(s):

Metric Learning ◽

Weighted Average ◽

Spatial Location ◽

Feature Maps ◽

Local Descriptor ◽

Qualitative And Quantitative ◽

Learning Tasks ◽

Deep Metric Learning ◽

High Computational Efficiency ◽

Channel Dimension

In this paper, we aim to enhance self-attention (SA) mechanism for deep metric learning in visual perception, by capturing richer contextual dependencies in visual data. To this end, we propose a novel module, named compressed self-attention (CSA), which significantly reduces the computation and memory cost with a neglectable decrease in accuracy with respect to the original SA mechanism, thanks to the following two characteristics: i) it only needs to compute a small number of base attention maps for a small number of base feature vectors; and ii) the output at each spatial location can be simply obtained by an adaptive weighted average of the outputs calculated from the base attention maps. The high computational efficiency of CSA enables the application to high-resolution shallow layers in convolutional neural networks with little additional cost. In addition, CSA makes it practical to further partition the feature maps into groups along the channel dimension and compute attention maps for features in each group separately, thus increasing the diversity of long-range dependencies and accordingly boosting the accuracy. We evaluate the performance of CSA via extensive experiments on two metric learning tasks: person re-identification and local descriptor learning. Qualitative and quantitative comparisons with latest methods demonstrate the significance of CSA in this topic.

Download Full-text

Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) ◽

10.1109/cvpr.2019.00495 ◽

2019 ◽

Cited By ~ 3

Author(s):

Tongtong Yuan ◽

Weihong Deng ◽

Jian Tang ◽

Yinan Tang ◽

Binghui Chen

Keyword(s):

Signal To Noise Ratio ◽

Metric Learning ◽

Distance Metric ◽

Signal To Noise ◽

Deep Metric Learning ◽

Noise Ratio

Download Full-text

MapCell: Learning a Comparative Cell Type Distance Metric With Siamese Neural Nets With Applications Toward Cell-Type Identification Across Experimental Datasets

Frontiers in Cell and Developmental Biology ◽

10.3389/fcell.2021.767897 ◽

2021 ◽

Vol 9 ◽

Author(s):

Winston Koh ◽

Shawn Hoon

Keyword(s):

Single Cell ◽

Metric Learning ◽

Cell Types ◽

Neural Nets ◽

Distance Metric ◽

Cell Type ◽

Training Set ◽

Aggregated Data ◽

Training Approach ◽

Deep Metric Learning

Large collections of annotated single-cell RNA sequencing (scRNA-seq) experiments are being generated across different organs, conditions and organisms on different platforms. The diversity, volume and complexity of this aggregated data requires new analysis techniques to extract actionable knowledge. Fundamental to most analysis are key abilities such as: identification of similar cells across different experiments and transferring annotations from an annotated dataset to an unannotated one. There have been many strategies explored in achieving these goals, and they focuses primarily on aligning and re-clustering datasets of interest. In this work, we are interested in exploring the applicability of deep metric learning methods as a form of distance function to capture similarity between cells and facilitate the transfer of cell type annotation for similar cells across different experiments. Toward this aim, we developed MapCell, a few-shot training approach using Siamese Neural Networks (SNNs) to learn a generalizable distance metric that can differentiate between single cell types. Requiring only a small training set, we demonstrated that SNN derived distance metric can perform accurate transfer of annotation across different scRNA-seq platforms, batches, species and also aid in flagging novel cell types.

Download Full-text

General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2017/341 ◽

2017 ◽

Cited By ~ 1

Author(s):

Yong Luo ◽

Yonggang Wen ◽

Tongliang Liu ◽

Dacheng Tao

Keyword(s):

Transfer Learning ◽

Metric Learning ◽

Learning Task ◽

Distance Metric Learning ◽

Distance Metric ◽

Target Domain ◽

Feature Representations ◽

Transfer Distance ◽

Learning Tasks ◽

Feature Spaces

Transfer learning aims to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. Recently, transfer distance metric learning (TDML) has attracted lots of interests, but most of these methods assume that feature representations for the source and target learning tasks are the same. Hence, they are not suitable for the applications, in which the data are from heterogeneous domains (feature spaces, modalities and even semantics). Although some existing heterogeneous transfer learning (HTL) approaches is able to handle such domains, they lack flexibility in real-world applications, and the learned transformations are often restricted to be linear. We therefore develop a general and flexible heterogeneous TDML (HTDML) framework based on the knowledge fragment transfer strategy. In the proposed HTDML, any (linear or nonlinear) distance metric learning algorithms can be employed to learn the source metric beforehand. Then a set of knowledge fragments are extracted from the pre-learned source metric to help target metric learning. In addition, either linear or nonlinear distance metric can be learned for the target domain. Extensive experiments on both scene classification and object recognition demonstrate superiority of the proposed method.

Download Full-text

Safe Triplet Screening for Distance Metric Learning

Neural Computation ◽

10.1162/neco_a_01240 ◽

2019 ◽

Vol 31 (12) ◽

pp. 2432-2491

Author(s):

Tomoki Yoshida ◽

Ichiro Takeuchi ◽

Masayuki Karasuyama

Keyword(s):

Optimization Problem ◽

Metric Learning ◽

Computational Cost ◽

Training Data ◽

Small Data ◽

Data Sets ◽

Distance Metric Learning ◽

Distance Metric ◽

Data Set ◽

Optimal Distance

Distance metric learning has been widely used to obtain the optimal distance function based on the given training data. We focus on a triplet-based loss function, which imposes a penalty such that a pair of instances in the same class is closer than a pair in different classes. However, the number of possible triplets can be quite large even for a small data set, and this considerably increases the computational cost for metric optimization. In this letter, we propose safe triplet screening that identifies triplets that can be safely removed from the optimization problem without losing the optimality. In comparison with existing safe screening studies, triplet screening is particularly significant because of the huge number of possible triplets and the semidefinite constraint in the optimization problem. We demonstrate and verify the effectiveness of our screening rules by using several benchmark data sets.

Download Full-text