PyTorch Metric Learning

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.

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

References in corpus (3)

• Scikit-learn: Machine Learning in Python
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• The NumPy array: a structure for efficient numerical computation

Cited by in corpus (11)

• DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
• Understanding and Mitigating Annotation Bias in Facial Expression Recognition
• Robust and Decomposable Average Precision for Image Retrieval
• Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
• Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning
• MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
• Contrastive Fine-tuning Improves Robustness for Neural Rankers
• Incremental Class Learning using Variational Autoencoders with Similarity Learning
• Multi-granularity for knowledge distillation
• Linking Social Media Posts to News with Siamese Transformers
• Video Surveillance for Road Traffic Monitoring