The Group Loss for Deep Metric Learning

12/01/2019
by   Ismail Elezi, et al.
46

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We show state-of-the-art results on clustering and image retrieval on several datasets, and show the potential of our method when combined with other techniques such as ensembles

READ FULL TEXT

page 6

page 10

research
05/30/2019

The General Pair-based Weighting Loss for Deep Metric Learning

Deep metric learning aims at learning the distance metric between pair o...
research
01/15/2018

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

Learning similarity functions between image pairs with deep neural netwo...
research
02/15/2021

Learning Intra-Batch Connections for Deep Metric Learning

The goal of metric learning is to learn a function that maps samples to ...
research
12/11/2017

Deep metric learning for multi-labelled radiographs

Many radiological studies can reveal the presence of several co-existing...
research
07/17/2019

Deep Metric Learning with Alternating Projections onto Feasible Sets

During the training of networks for distance metric learning, minimizers...
research
06/01/2023

Class Anchor Margin Loss for Content-Based Image Retrieval

The performance of neural networks in content-based image retrieval (CBI...
research
11/17/2020

Towards Improved and Interpretable Deep Metric Learning via Attentive Grouping

Grouping has been commonly used in deep metric learning for computing di...

Please sign up or login with your details

Forgot password? Click here to reset