Unifying Specialist Image Embedding into Universal Image Embedding

TL;DR

This paper introduces a novel knowledge distillation approach to train a universal image embedding model that matches the performance of specialist models across multiple domains by transforming distance metrics into probabilistic distributions.

Contribution

It proposes a new distillation method that converts absolute image distances into distributions and minimizes KL-divergence, enabling a single universal embedding model to perform well across various domains.

Findings

Universal embedding matches specialist performance on multiple domains.

The probabilistic distillation method outperforms traditional distance-based methods.

Validated on several public datasets with positive results.

Abstract

Deep image embedding provides a way to measure the semantic similarity of two images. It plays a central role in many applications such as image search, face verification, and zero-shot learning. It is desirable to have a universal deep embedding model applicable to various domains of images. However, existing methods mainly rely on training specialist embedding models each of which is applicable to images from a single domain. In this paper, we study an important but unexplored task: how to train a single universal image embedding model to match the performance of several specialists on each specialist's domain. Simply fusing the training data from multiple domains cannot solve this problem because some domains become overfitted sooner when trained together using existing methods. Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem. In contrast to existing embedding distillation methods that distill the absolute distances between images, we transform the absolute distances between images into a probabilistic distribution and minimize the KL-divergence between the distributions of the specialists and the universal embedding. Using several public datasets, we validate that our proposed method accomplishes the goal of universal image embedding.