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
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.
Ranked #3 on
Video Alignment
on UPenn Action
We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER).
Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming.
Deep metric learning papers from the past four years have consistently claimed great advances in accuracy, often more than doubling the performance of decade-old methods.
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 $s_n$.
Ranked #1 on
Metric Learning
on CUB-200-2011
FACE RECOGNITION IMAGE RETRIEVAL METRIC LEARNING PERSON RE-IDENTIFICATION
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.
Ranked #3 on
Person Re-Identification
on CUHK03
(Rank-5 metric)
metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms.
This work considers the problem of domain shift in person re-identification. Being trained on one dataset, a re-identification model usually performs much worse on unseen data.
Ranked #13 on
Person Re-Identification
on MSMT17
DOMAIN GENERALIZATION FACE RECOGNITION METRIC LEARNING PERSON RE-IDENTIFICATION
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.
FEW-SHOT IMAGE CLASSIFICATION LANGUAGE MODELLING METRIC LEARNING OMNIGLOT ONE-SHOT LEARNING
This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model.
Ranked #2 on
Image Retrieval
on In-Shop