About

The goal of Metric Learning is to learn a representation function that maps objects into an embedded space. The distance in the embedded space should preserve the objects’ similarity — similar objects get close and dissimilar objects get far away. Various loss functions have been developed for Metric Learning. For example, the contrastive loss guides the objects from the same class to be mapped to the same point and those from different classes to be mapped to different points whose distances are larger than a margin. Triplet loss is also popular, which requires the distance between the anchor sample and the positive sample to be smaller than the distance between the anchor sample and the negative sample.

Source: Road Network Metric Learning for Estimated Time of Arrival

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Time-Contrastive Networks: Self-Supervised Learning from Video

23 Apr 2017tensorflow/models

While representations are learned from an unlabeled collection of task-related videos, robot behaviors such as pouring are learned by watching a single 3rd-person demonstration by a human.

METRIC LEARNING SELF-SUPERVISED LEARNING VIDEO ALIGNMENT

Disentangling by Subspace Diffusion

NeurIPS 2020 deepmind/deepmind-research

We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER).

METRIC LEARNING REPRESENTATION LEARNING

PyTorch Metric Learning

20 Aug 2020KevinMusgrave/pytorch-metric-learning

Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming.

METRIC LEARNING

A Metric Learning Reality Check

ECCV 2020 KevinMusgrave/pytorch-metric-learning

Deep metric learning papers from the past four years have consistently claimed great advances in accuracy, often more than doubling the performance of decade-old methods.

METRIC LEARNING

Circle Loss: A Unified Perspective of Pair Similarity Optimization

CVPR 2020 layumi/Person_reID_baseline_pytorch

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$.

FACE RECOGNITION IMAGE RETRIEVAL METRIC LEARNING PERSON RE-IDENTIFICATION

In Defense of the Triplet Loss for Person Re-Identification

22 Mar 2017adambielski/siamese-triplet

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning.

Ranked #3 on Person Re-Identification on CUHK03 (Rank-5 metric)

METRIC LEARNING PERSON RE-IDENTIFICATION

metric-learn: Metric Learning Algorithms in Python

13 Aug 2019scikit-learn-contrib/metric-learn

metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms.

METRIC LEARNING MODEL SELECTION

Matching Networks for One Shot Learning

NeurIPS 2016 oscarknagg/few-shot

Our algorithm improves one-shot accuracy on ImageNet from 87. 6% to 93. 2% and from 88. 0% to 93. 8% on Omniglot compared to competing approaches.

FEW-SHOT IMAGE CLASSIFICATION LANGUAGE MODELLING METRIC LEARNING OMNIGLOT ONE-SHOT LEARNING

Cross-Batch Memory for Embedding Learning

CVPR 2020 bnu-wangxun/Deep_Metric

This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model.

IMAGE RETRIEVAL METRIC LEARNING