Metric Learning
554 papers with code • 8 benchmarks • 32 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
In-Shop
VIPeR
Structured3D
ABO
CARS196
VeRi-Wild
WildDeepfake
Latest papers
DUCK: Distance-based Unlearning via Centroid Kinematics
ocram17/duck
•
•
Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models.
Robust Concept Erasure via Kernelized Rate-Distortion Maximization
brcsomnath/kram
•
•
NeurIPS 2023
Distributed representations provide a vector space that captures meaningful relationships between data instances.
Deep Hashing via Householder Quantization
Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques.
Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling
In practice, these dominant pipeline models may be limited in computational efficiency and generalization capacity because of non-parallel inference and context-free discrete label embeddings.
Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss
The deviation of a classification model is caused by both class-wise and attribute-wise imbalance.
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration.
Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning
We propose to train a GAN-based synthetic-image generator, translating available day-time image examples into night images.
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
billpsomas/simpool
•
•
ICCV 2023
By discussing the properties of each group of methods, we derive SimPool, a simple attention-based pooling mechanism as a replacement of the default one for both convolutional and transformer encoders.
Deep Attentive Time Warping
matsuo-shinnosuke/deep-attentive-time-warping
•
•
Unlike other learnable models using DTW for warping, our model predicts all local correspondences between two time series and is trained based on metric learning, which enables it to learn the optimal data-dependent warping for the target task.
Introspective Deep Metric Learning
wangck20/idml
•
•
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
