Realigned Softmax Warping for Deep Metric Learning

TL;DR

This paper introduces a novel class of loss functions for deep metric learning that utilize a warping function within the Euclidean space to better control class separability and compactness, achieving state-of-the-art results.

Contribution

It proposes a new warping-based loss function that enhances control over embedding space formation in deep metric learning.

Findings

Achieved competitive, state-of-the-art results on various benchmarks.

Demonstrated the effectiveness of warping functions in controlling embedding space forces.

Provided a simple example of a warping function that improves metric learning performance.

Abstract

Deep Metric Learning (DML) loss functions traditionally aim to control the forces of separability and compactness within an embedding space so that the same class data points are pulled together and different class ones are pushed apart. Within the context of DML, a softmax operation will typically normalize distances into a probability for optimization, thus coupling all the push/pull forces together. This paper proposes a potential new class of loss functions that operate within a euclidean domain and aim to take full advantage of the coupled forces governing embedding space formation under a softmax. These forces of compactness and separability can be boosted or mitigated within controlled locations at will by using a warping function. In this work, we provide a simple example of a warping function and use it to achieve competitive, state-of-the-art results on various metric learning benchmarks.