Constellation Loss: Improving the efficiency of deep metric learning loss functions for optimal embedding

05/25/2019
by   Alfonso Medela, et al.
0

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling complex scenarios with the presence of many classes and scarcity on the number of images per class not only work to build classifiers, but to many other applications where measuring similarity is the key. Deep Neural Networks trained via metric learning also offer the possibility to solve few-shot learning problems. Currently used state of the art loss functions such as triplet and contrastive loss functions, still suffer from slow convergence due to the selection of effective training samples that has been partially solved by the multi-class N-pair loss by simultaneously adding additional samples from the different classes. In this work, we extend triplet and multiclass-N-pair loss function by proposing the constellation loss metric where the distances among all class combinations are simultaneously learned. We have compared our constellation loss for visual class embedding showing that our loss function over-performs the other methods by obtaining more compact clusters while achieving better classification results.

READ FULL TEXT
research
02/06/2021

MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking

One of the central tasks of multi-object tracking involves learning a di...
research
10/04/2021

Incremental Class Learning using Variational Autoencoders with Similarity Learning

Catastrophic forgetting in neural networks during incremental learning r...
research
02/16/2021

Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining

Few-shot learning aims to generalize unseen classes that appear during t...
research
01/27/2022

Dissecting the impact of different loss functions with gradient surgery

Pair-wise loss is an approach to metric learning that learns a semantic ...
research
04/05/2020

Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks

Siamese neural network is a very powerful architecture for both feature ...
research
08/04/2017

Deep Metric Learning with Angular Loss

The modern image search system requires semantic understanding of image,...

Please sign up or login with your details

Forgot password? Click here to reset