Metric Learning

423 papers with code • 5 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

Most implemented papers

In Defense of the Triplet Loss for Person Re-Identification

layumi/Person_reID_baseline_pytorch 22 Mar 2017

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.

Matching Networks for One Shot Learning

oscarknagg/few-shot NeurIPS 2016

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.

Additive Margin Softmax for Face Verification

happynear/AMSoftmax 17 Jan 2018

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.

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 $s_n$.

Semantic Instance Segmentation with a Discriminative Loss Function

Wizaron/instance-segmentation-pytorch 8 Aug 2017

In this work we propose to tackle the problem with a discriminative loss function, operating at the pixel level, that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step.

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

Confusezius/Deep-Metric-Learning-Baselines ICML 2020

Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year.

Sampling Matters in Deep Embedding Learning

CompVis/metric-learning-divide-and-conquer ICCV 2017

In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions.

Batch DropBlock Network for Person Re-identification and Beyond

daizuozhuo/batch-feature-erasing-network ICCV 2019

In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch.

Deep Cosine Metric Learning for Person Re-Identification

nwojke/cosine_metric_learning 2 Dec 2018

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.

PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

kaixin96/PANet ICCV 2019

In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set.