Metric Learning
484 papers with code • 8 benchmarks • 31 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
These leaderboards are used to track progress in Metric Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Metric Learning models and implementationsDatasets
CUB-200-2011
CASIA-WebFace
Stanford Online Products
VIPeR
In-Shop
Structured3D
CARS196
VeRi-Wild
WildDeepfake
Google Landmarks Dataset v2
Most implemented papers
Associative Alignment for Few-shot Image Classification
ML-Bee/associative-alignment-fs
•
•
ECCV 2020
Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes.
Ranking and Classification driven Feature Learning for Person Re_identification
Qidian213/Ranked_Person_ReID
•
•
However, the method that using Triplet loss as loss function converges slowly, and the method in which pull features of the same class as close as possible in features space leads to poor feature stability.
Distance Metric Learning for Graph Structured Data
Hence, we propose a supervised distance metric learning method for the graph classification problem.
An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality
spitis/deepnorms
•
•
ICLR 2020
When defining distances, the triangle inequality has proven to be a useful constraint, both theoretically--to prove convergence and optimality guarantees--and empirically--as an inductive bias.
CoLES: Contrastive Learning for Event Sequences with Self-Supervision
We address the problem of self-supervised learning on discrete event sequences generated by real-world users.
Generalized Product Quantization Network for Semi-supervised Image Retrieval
youngkyunJang/GPQ
•
•
CVPR 2020
Image retrieval methods that employ hashing or vector quantization have achieved great success by taking advantage of deep learning.
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
clovaai/embedding-expansion
•
•
CVPR 2020
Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information.
OpenGAN: Open Set Generative Adversarial Networks
Using a state-of-the-art metric learning model that encodes both class-level and fine-grained semantic information, we are able to generate samples that are semantically similar to a given source image.
Maximum Density Divergence for Domain Adaptation
lijin118/ATM
•
•
In this paper, we propose a new domain adaptation method named Adversarial Tight Match (ATM) which enjoys the benefits of both adversarial training and metric learning.
DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
Confusezius/ECCV2020_DiVA_MultiFeature_DML
•
•
ECCV 2020
Visual Similarity plays an important role in many computer vision applications.
