scholarly journals An approach to partial occlusion using deep metric learning

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>

scholarly journals Deep Metric Learning: A Survey

Symmetry ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1066 ◽  
Author(s):  
Kaya ◽  
Bilge
Keyword(s):  
Metric Learning ◽  
Sampling Strategy ◽  
Distance Metric ◽  
Linear Projection ◽  
Learning Tasks ◽  
Optimal Distance ◽  
Quantitative Results ◽  
Deep Metric Learning ◽  
Real World Problems ◽  
Comprehensive Study

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.

scholarly journals Revisiting giraffe photo-identification using deep learning and network analysis

2020 ◽  
Author(s):  
Vincent Miele ◽  
Gaspard Dussert ◽  
Bruno Spataro ◽  
Simon Chamaillé-Jammes ◽  
Dominique Allainé ◽  
...  
Keyword(s):  
Metric Learning ◽  
Simple Task ◽  
Photo Identification ◽  
Software Packages ◽  
Animal Populations ◽  
In The Wild ◽  
Capture Recapture ◽  
Deep Metric Learning ◽  
Similarity Networks ◽  
Do So

AbstractAn increasing number of research programs rely on photographic capture-recapture (vs. direct marking) of individuals to study distribution and demography within animal populations. Photo-identification of individuals living in the wild is sometimes feasible using idiosyncratic coat or skin patterns, like for giraffes. When performed manually, the task is tedious and becomes almost impossible as populations grow in size. Computer vision techniques are an appealing and unavoidable help to tackle this apparently simple task in the big-data era. In this context, we propose to revisit giraffe re-identification using convolutional neural networks (CNNs).We first developed an end-to-end pipeline to retrieve a comprehensive set of re-identified giraffes from about 4, 000 raw photographs. To do so, we combined CNN-based object detection, SIFT pattern matching, and image similarity networks. We then quantified the performance of deep metric learning to retrieve the identity of known and unknown individuals. The re-identification performance of CNNs reached a top 5 accuracy of about 90%. Fully based on open-source software packages, our work paves the way for further attempts to build CNN-based pipelines for re-identification of individual animals, in giraffes but also in other species.

scholarly journals Compressed Self-Attention for Deep Metric Learning

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.

scholarly journals Multi-view Spectral Clustering Network

2019 ◽  
Author(s):  
Zhenyu Huang ◽  
Joey Tianyi Zhou ◽  
Xi Peng ◽  
Changqing Zhang ◽  
Hongyuan Zhu ◽  
...  
Keyword(s):  
Spectral Clustering ◽  
Euclidean Distance ◽  
Metric Learning ◽  
Matrix Decomposition ◽  
Single View ◽  
Local Invariance ◽  
Cluster Data ◽  
The Neural Network ◽  
Deep Metric Learning ◽  
Traditional Approaches

Multi-view clustering aims to cluster data from diverse sources or domains, which has drawn considerable attention in recent years. In this paper, we propose a novel multi-view clustering method named multi-view spectral clustering network (MvSCN) which could be the first deep version of multi-view spectral clustering to the best of our knowledge. To deeply cluster multi-view data, MvSCN incorporates the local invariance within every single view and the consistency across different views into a novel objective function, where the local invariance is defined by a deep metric learning network rather than the Euclidean distance adopted by traditional approaches. In addition, we enforce and reformulate an orthogonal constraint as a novel layer stacked on an embedding network for two advantages, i.e. jointly optimizing the neural network and performing matrix decomposition and avoiding trivial solutions. Extensive experiments on four challenging datasets demonstrate the effectiveness of our method compared with 10 state-of-the-art approaches in terms of three evaluation metrics.

Dysarthric Speech Recognition Based on Deep Metric Learning

2020 ◽  
Author(s):  
Yuki Takashima ◽  
Ryoichi Takashima ◽  
Tetsuya Takiguchi ◽  
Yasuo Ariki
Keyword(s):  
Speech Recognition ◽  
Metric Learning ◽  
Deep Metric Learning ◽  
Dysarthric Speech

scholarly journals Ranked List Loss for Deep Metric Learning

2021 ◽  
pp. 1-1
Author(s):  
Xinshao Wang ◽  
Yang Hua ◽  
Elyor Kodirov ◽  
Neil M Robertson
Keyword(s):  
Metric Learning ◽  
Deep Metric Learning ◽  
Ranked List

scholarly journals Predicting TCR-Epitope Binding Specificity Using Deep Metric Learning and Multimodal Learning

Genes ◽  
2021 ◽  
Vol 12 (4) ◽  
pp. 572
Author(s):  
Alan M. Luu ◽  
Jacob R. Leistico ◽  
Tim Miller ◽  
Somang Kim ◽  
Jun S. Song
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Cytotoxic T Cells ◽  
Metric Learning ◽  
Binding Specificity ◽  
Class I ◽  
Multimodal Learning ◽  
Binding Prediction ◽  
Deep Metric Learning ◽  
Epitope Binding

Understanding the recognition of specific epitopes by cytotoxic T cells is a central problem in immunology. Although predicting binding between peptides and the class I Major Histocompatibility Complex (MHC) has had success, predicting interactions between T cell receptors (TCRs) and MHC class I-peptide complexes (pMHC) remains elusive. This paper utilizes a convolutional neural network model employing deep metric learning and multimodal learning to perform two critical tasks in TCR-epitope binding prediction: identifying the TCRs that bind a given epitope from a TCR repertoire, and identifying the binding epitope of a given TCR from a list of candidate epitopes. Our model can perform both tasks simultaneously and reveals that inconsistent preprocessing of TCR sequences can confound binding prediction. Applying a neural network interpretation method identifies key amino acid sequence patterns and positions within the TCR, important for binding specificity. Contrary to common assumption, known crystal structures of TCR-pMHC complexes show that the predicted salient amino acid positions are not necessarily the closest to the epitopes, implying that physical proximity may not be a good proxy for importance in determining TCR-epitope specificity. Our work thus provides an insight into the learned predictive features of TCR-epitope binding specificity and advances the associated classification tasks.

Sign in / Sign up

Export Citation Format

Share Document