PyTorch Metric Learning

2020/08/20 by Kevin Musgrave, Serge Belongie, Musgrave, Kevin +3 · 6 citations
Computer Science · #Face and Expression Recognition #Image Retrieval and Classification Techniques #Machine Learning and Data Classification #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.2008.09164

Code and documentation is available at https://www.github.com/KevinMusgrave/pytorch-metric-learning

arxiv created 2020/08/20 · arxiv updated 2020/08/24

Abstract

Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming. PyTorch Metric Learning is an open source library that aims to remove this barrier for both researchers and practitioners. The modular and flexible design allows users to easily try out different combinations of algorithms in their existing code. It also comes with complete train/test workflows, for users who want results fast. Code and documentation is available at https://www.github.com/KevinMusgrave/pytorch-metric-learning.

Cited by

• Video Surveillance for Road Traffic Monitoring
• Face and voice cross-modal association with learning convex feature embedding
• Understanding and Mitigating Annotation Bias in Facial Expression Recognition
• Linking Social Media Posts to News with Siamese Transformers
• DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
• MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
• Incremental Class Learning using Variational Autoencoders with Similarity Learning
• Improving Generalization in MRI-Based Deep Learning Models for Total Knee Replacement Prediction

Related

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Torchbearer: A Model Fitting Library for PyTorch
• PyTorch Adapt
• A Metric Learning Reality Check
• Torchmeta: A Meta-Learning library for PyTorch