Metric Learning
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
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.
In Defense of the Triplet Loss for Person Re-Identification
• VisualComputingInstitute/triplet-reid
• 
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.
#11 best model for
Person Re-Identification
on Market-1501
Additive Margin Softmax for Face Verification
In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.
NormFace: L2 Hypersphere Embedding for Face Verification
We show that both strategies, and small variants, consistently improve performance by between 0. 2% to 0. 4% on the LFW dataset based on two models.
Matching Networks for One Shot Learning
NeurIPS 2016
• AntreasAntoniou/MatchingNetworks
•
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.
#4 best model for
Few-Shot Image Classification
on OMNIGLOT - 1-Shot Learning
FEW-SHOT IMAGE CLASSIFICATION LANGUAGE MODELLING METRIC LEARNING ONE-SHOT LEARNING
Deep Cosine Metric Learning for Person Re-Identification
• nwojke/cosine_metric_learning
•
Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities.
Deep metric learning using Triplet network
Deep learning has proven itself as a successful set of models for learning useful semantic representations of data.
Batch Feature Erasing for Person Re-identification and Beyond
• daizuozhuo/batch-feature-erasing-network
• 
The two branches consist of a conventional global branch and a feature erasing branch where the BFE strategy is applied.
A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets
• NEU-Gou/awesome-reid-dataset
To ensure a fair comparison, all of the approaches were implemented using a unified code library that includes 11 feature extraction algorithms and 22 metric learning and ranking techniques.