About

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 METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Latest papers with code

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

ICLR 2021 twke18/SPML

Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles.

METRIC LEARNING WEAKLY SUPERVISED SEGMENTATION WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

6
03 May 2021

Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification

4 Apr 2021shengcailiao/QAConv

Then, each mini batch is composed of a randomly selected class and its nearest neighboring classes so as to provide informative and challenging examples for learning.

GENERALIZABLE PERSON RE-IDENTIFICATION GRAPH SAMPLING METRIC LEARNING REPRESENTATION LEARNING TRANSFER LEARNING

89
04 Apr 2021

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

30 Mar 2021alibaba-edu/Ranking-based-Instance-Selection

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.

METRIC LEARNING

3
30 Mar 2021

Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning

29 Mar 2021navervision/proxy-synthesis

One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes.

IMAGE RETRIEVAL METRIC LEARNING

6
29 Mar 2021

Multi-Facet Recommender Networks with Spherical Optimization

27 Mar 2021Melinda315/MARS

Metric learning has been proposed to capture user-item interactions from implicit feedback, but existing methods only represent users and items in a single metric space, ignoring the fact that users can have multiple preferences and items can have multiple properties, which leads to potential conflicts limiting their performance in recommendation.

METRIC LEARNING RECOMMENDATION SYSTEMS REPRESENTATION LEARNING

5
27 Mar 2021

Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales

22 Mar 2021SupetZYK/DynamicMetricLearning

%We argue that such flexibility is also important for deep metric learning, because different visual concepts indeed correspond to different semantic scales.

METRIC LEARNING

19
22 Mar 2021

Rethinking Relational Encoding in Language Model: Pre-Training for General Sequences

18 Mar 2021mmcdermott/structure_preserving_pre-training

We also design experiments on a variety of synthetic datasets and new graph-augmented datasets of proteins and scientific abstracts.

LANGUAGE MODELLING METRIC LEARNING NATURAL LANGUAGE UNDERSTANDING

4
18 Mar 2021

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

16 Mar 2021cvg/pixloc

In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms.

CAMERA LOCALIZATION METRIC LEARNING POSE ESTIMATION

166
16 Mar 2021