scholarly journals Deep metric learning for bioacoustic classification: Overcoming training data scarcity using dynamic triplet loss

2019 ◽  
Vol 146 (1) ◽  
pp. 534-547 ◽  
Author(s):  
Anshul Thakur ◽  
Daksh Thapar ◽  
Padmanabhan Rajan ◽  
Aditya Nigam
Keyword(s):  
Metric Learning ◽  
Training Data ◽  
Data Scarcity ◽  
Triplet Loss ◽  
Deep Metric Learning

scholarly journals Enhancing Multi-tissue and Multi-scale Cell Nuclei Segmentation with Deep Metric Learning

2020 ◽  
Vol 10 (2) ◽  
pp. 615 ◽  
Author(s):  
Tomas Iesmantas ◽  
Agne Paulauskaite-Taraseviciene ◽  
Kristina Sutiene
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Metric Learning ◽  
Cell Nuclei ◽  
Similarity Coefficients ◽  
Clinical Practices ◽  
Nuclei Segmentation ◽  
Wide Range ◽  
Triplet Loss ◽  
Deep Metric Learning

(1) Background: The segmentation of cell nuclei is an essential task in a wide range of biomedical studies and clinical practices. The full automation of this process remains a challenge due to intra- and internuclear variations across a wide range of tissue morphologies, differences in staining protocols and imaging procedures. (2) Methods: A deep learning model with metric embeddings such as contrastive loss and triplet loss with semi-hard negative mining is proposed in order to accurately segment cell nuclei in a diverse set of microscopy images. The effectiveness of the proposed model was tested on a large-scale multi-tissue collection of microscopy image sets. (3) Results: The use of deep metric learning increased the overall segmentation prediction by 3.12% in the average value of Dice similarity coefficients as compared to no metric learning. In particular, the largest gain was observed for segmenting cell nuclei in H&E -stained images when deep learning network and triplet loss with semi-hard negative mining were considered for the task. (4) Conclusion: We conclude that deep metric learning gives an additional boost to the overall learning process and consequently improves the segmentation performance. Notably, the improvement ranges approximately between 0.13% and 22.31% for different types of images in the terms of Dice coefficients when compared to no metric deep learning.

scholarly journals Stamping Tool Conditions Diagnosis: A Deep Metric Learning Approach

2021 ◽  
Vol 11 (15) ◽  
pp. 6959
Author(s):  
Zaky Dzulfikri ◽  
Pin-Wei Su ◽  
Chih-Yung Huang
Keyword(s):  
Neural Network ◽  
Metric Learning ◽  
Training Data ◽  
Probability Method ◽  
Learning Approach ◽  
Test Results ◽  
Complex Signals ◽  
Intelligent Monitoring ◽  
Deep Metric Learning

Stamping processes remain crucial in manufacturing processes; therefore, diagnosing the condition of stamping tools is critical. One of the challenges in diagnosing stamping tool conditions is that traditionally, the tools need to be visually checked, and the production processes thus need to be halted. With the development of Industry 4.0, intelligent monitoring systems have been developed by using accelerometers and algorithms to diagnose the wear classification of stamping tools. Although several deep learning models such as the convolutional neural network (CNN), auto encoder (AE), and recurrent neural network (RNN) models have demonstrated promising results for classifying complex signals including accelerometer signals, the practicality of those methods are restricted due to the flexibility of adding new classes and low accuracy when faced to low numbers of samples per class. In this study, we applied deep metric learning (DML) methods to overcome these problems. DML involves extracting meaningful features using feature extraction modules to map inputs into embedding features. We compared the probability method, the contrastive method, and a triplet network to determine which method was most suitable for our case. The experimental results revealed that, compared with other models, a triplet network can be more effectively trained with limited training data. The triplet network demonstrated the best test results of the compared methods in the noised test data. Finally, when tested using unseen class, the triplet network and the probability method demonstrated similar results.

scholarly journals Person Re-Identification by Pose Invariant Deep Metric Learning With Improved Triplet Loss

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 68089-68095 ◽  
Author(s):  
Min Chen ◽  
Yongxin Ge ◽  
Xin Feng ◽  
Chuanyun Xu ◽  
Dan Yang
Keyword(s):  
Metric Learning ◽  
Triplet Loss ◽  
Deep Metric Learning

scholarly journals Deep metric attention learning for skin lesion classification in dermoscopy images

2022 ◽  
Author(s):  
Xiaoyu He ◽  
Yong Wang ◽  
Shuang Zhao ◽  
Chunli Yao
Keyword(s):  
Skin Lesion ◽  
Metric Learning ◽  
Feature Representation ◽  
Training Procedure ◽  
Training Samples ◽  
Triplet Loss ◽  
Deep Metric Learning ◽  
Localization Ability ◽  
Lesion Localization ◽  
Lesion Classification

AbstractCurrently, convolutional neural networks (CNNs) have made remarkable achievements in skin lesion classification because of their end-to-end feature representation abilities. However, precise skin lesion classification is still challenging because of the following three issues: (1) insufficient training samples, (2) inter-class similarities and intra-class variations, and (3) lack of the ability to focus on discriminative skin lesion parts. To address these issues, we propose a deep metric attention learning CNN (DeMAL-CNN) for skin lesion classification. In DeMAL-CNN, a triplet-based network (TPN) is first designed based on deep metric learning, which consists of three weight-shared embedding extraction networks. TPN adopts a triplet of samples as input and uses the triplet loss to optimize the embeddings, which can not only increase the number of training samples, but also learn the embeddings robust to inter-class similarities and intra-class variations. In addition, a mixed attention mechanism considering both the spatial-wise and channel-wise attention information is designed and integrated into the construction of each embedding extraction network, which can further strengthen the skin lesion localization ability of DeMAL-CNN. After extracting the embeddings, three weight-shared classification layers are used to generate the final predictions. In the training procedure, we combine the triplet loss with the classification loss as a hybrid loss to train DeMAL-CNN. We compare DeMAL-CNN with the baseline method, attention methods, advanced challenge methods, and state-of-the-art skin lesion classification methods on the ISIC 2016 and ISIC 2017 datasets, and test its generalization ability on the PH2 dataset. The results demonstrate its effectiveness.

scholarly journals Birdsong Phrase Verification and Classification Using Siamese Neural Networks

2021 ◽  
Author(s):  
Santiago Renteria ◽  
Edgar Vallejo ◽  
Charles Taylor
Keyword(s):  
Neural Networks ◽  
Metric Learning ◽  
Class Imbalance ◽  
Learning Task ◽  
Interdisciplinary Studies ◽  
Training Data ◽  
Data Scarcity ◽  
Origin And Evolution ◽  
Shot Classification ◽  
And Function

Bird vocalizations have been the focus of a wide variety of interdisciplinary studies in bioacoustics and neuroethology since they serve as models of motor control, learning and auditory perception. Yet, researchers have only begun to shed light on the structure and function of birdsong. Hypotheses abound, but still there is little agreement as how songs should be analyzed. One of the main challenges has been to classify acoustic units (syllables) from birdsong recordings, a task requiring robust classification algorithms capable of generalizing to unseen instances and dealing with data scarcity. Systematically detecting changes in syllable repertoires can help biologists to understand the origin and evolution of birdsong.  The process of learning good features to discriminate among numerous and different sound classes is computationally expensive. Moreover, it might be impossible to achieve acceptable performance in cases where training data is scarce and classes are unbalanced. To address this issue, we propose a few-shot learning task in which an algorithm must make predictions given only a few instances of each class. We compared the performance of different Siamese Neural Networks at metric learning over the set of Cassini's Vireo syllables. Then, the network features were reused for the few-shot classification task. With this approach we overcame the limitations of data scarcity and class imbalance while achieving state-of-the-art performance.

scholarly journals Deep Metric Learning with Hierarchical Triplet Loss

2018 ◽  
pp. 272-288 ◽  
Author(s):  
Weifeng Ge ◽  
Weilin Huang ◽  
Dengke Dong ◽  
Matthew R. Scott
Keyword(s):  
Metric Learning ◽  
Triplet Loss ◽  
Deep Metric Learning

scholarly journals High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery

2020 ◽  
Vol 12 (16) ◽  
pp. 2603
Author(s):  
Jian Kang ◽  
Rubén Fernández-Beltrán ◽  
Zhen Ye ◽  
Xiaohua Tong ◽  
Pedram Ghamisi ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Semantic Information ◽  
Metric Spaces ◽  
Metric Learning ◽  
Training Data ◽  
Deep Metric Learning ◽  
Class Labels ◽  
Image Pairs ◽  
Decision Boundaries

Deep metric learning has recently received special attention in the field of remote sensing (RS) scene characterization, owing to its prominent capabilities for modeling distances among RS images based on their semantic information. Most of the existing deep metric learning methods exploit pairwise and triplet losses to learn the feature embeddings with the preservation of semantic-similarity, which requires the construction of image pairs and triplets based on the supervised information (e.g., class labels). However, generating such semantic annotations becomes a completely unaffordable task in large-scale RS archives, which may eventually constrain the availability of sufficient training data for this kind of models. To address this issue, we reformulate the deep metric learning scheme in a semi-supervised manner to effectively characterize RS scenes. Specifically, we aim at learning metric spaces by utilizing the supervised information from a small number of labeled RS images and exploring the potential decision boundaries for massive sets of unlabeled aerial scenes. In order to reach this goal, a joint loss function, composed of a normalized softmax loss with margin and a high-rankness regularization term, is proposed, as well as its corresponding optimization algorithm. The conducted experiments (including different state-of-the-art methods and two benchmark RS archives) validate the effectiveness of the proposed approach for RS image classification, clustering and retrieval tasks. The codes of this paper are publicly available.

scholarly journals Function shaping in deep learning

2021 ◽  
Author(s):  
Ēvalds Urtāns
Keyword(s):  
Loss Function ◽  
Value Function ◽  
Metric Learning ◽  
Computer Game ◽  
Loss Functions ◽  
Identification Task ◽  
The Face ◽  
Triplet Loss ◽  
Deep Metric Learning ◽  
The Value Function

This work describes the importance of loss functions and related methods for deep reinforcement learning and deep metric learning. A novel MDQN loss function outperformed DDQN loss function in PLE computer game environments, and a novel Exponential Triplet loss function outperformed the Triplet loss function in the face re-identification task with VGGFace2 dataset reaching 85,7 % accuracy using zero-shot setting. This work also presents a novel UNet-RNN-Skip model to improve the performance of the value function for path planning tasks.

Sign in / Sign up

Export Citation Format

Share Document