Metric Learning
305 papers with code • 4 benchmarks • 26 datasets
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 Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
Datasets
CASIA-WebFace
VIPeR
Stanford Online Products
Isolet
CVUSA
Structured3D
VeRi-Wild
Greatest papers with code
Time-Contrastive Networks: Self-Supervised Learning from Video
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.
Ranked #3 on
Video Alignment
on UPenn Action
Disentangling by Subspace Diffusion
deepmind/deepmind-research
•
•
NeurIPS 2020
We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER).
PyTorch Metric Learning
KevinMusgrave/pytorch-metric-learning
•
•
Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming.
A Metric Learning Reality Check
KevinMusgrave/pytorch-metric-learning
•
•
ECCV 2020
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.
Circle Loss: A Unified Perspective of Pair Similarity Optimization
layumi/Person_reID_baseline_pytorch
•
•
CVPR 2020
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 $s_n$.
Ranked #3 on
Face Recognition
on CFP-FP
In Defense of the Triplet Loss for Person Re-Identification
adambielski/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)
Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
Person re-identification (ReID) is an important task in computer vision.
Improved Deep Metric Learning with Multi-class N-pair Loss Objective
PaddlePaddle/PaddleClas
•
•
NeurIPS 2016
Deep metric learning has gained much popularity in recent years, following the success of deep learning.
Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval
Learning Mahanalobis distance metrics in a high- dimensional feature space is very difficult especially when structural sparsity and low rank are enforced to improve com- putational efficiency in testing phase.
metric-learn: Metric Learning Algorithms in Python
metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms.