Learning Deep Optimal Embeddings with Sinkhorn Divergences

09/14/2022
by   Soumava Kumar Roy, et al.
0

Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data. Whilst these algorithms have achieved significant performance gains across a wide plethora of tasks, they have also failed to consider and increase comprehensive similarity constraints; thus learning a sub-optimal metric in the embedding space. Moreover, up until now; there have been few studies with respect to their performance in the presence of noisy labels. Here, we address the concern of learning a discriminative deep embedding space by designing a novel, yet effective Deep Class-wise Discrepancy Loss (DCDL) function that segregates the underlying similarity distributions (thus introducing class-wise discrepancy) of the embedding points between each and every class. Our empirical results across three standard image classification datasets and two fine-grained image recognition datasets in the presence and absence of noise clearly demonstrate the need for incorporating such class-wise similarity relationships along with traditional algorithms while learning a discriminative embedding space.

READ FULL TEXT

page 1

page 3

page 8

page 16

research
06/09/2020

Reducing Class Collapse in Metric Learning with Easy Positive Sampling

Metric learning seeks perceptual embeddings where visually similar insta...
research
07/30/2022

DAS: Densely-Anchored Sampling for Deep Metric Learning

Deep Metric Learning (DML) serves to learn an embedding function to proj...
research
02/27/2018

Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval

Deep distance metric learning (DDML), which is proposed to learn image s...
research
09/30/2018

Modeling Uncertainty with Hedged Instance Embedding

Instance embeddings are an efficient and versatile image representation ...
research
04/14/2023

Phantom Embeddings: Using Embedding Space for Model Regularization in Deep Neural Networks

The strength of machine learning models stems from their ability to lear...
research
11/22/2020

Enriching ImageNet with Human Similarity Judgments and Psychological Embeddings

Advances in object recognition flourished in part because of the availab...
research
04/16/2019

Beyond Correlation: A Path-Invariant Measure for Seismogram Similarity

Similarity search is a popular technique for seismic signal processing, ...

Please sign up or login with your details

Forgot password? Click here to reset