# Unifying Specialist Image Embedding into Universal Image Embedding

arXiv: https://arxiv.org/abs/2003.03701 · HTML: https://mlsanity.com/paper/2003.03701/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations](https://mlsanity.com/paper/2309.01858/) (2023)
- [UDON: Universal Dynamic Online distillatioN for generic image representations](https://mlsanity.com/paper/2406.08332/) (2024)
- [Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks](https://mlsanity.com/paper/2107.01354/) (2021)
- [Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval](https://mlsanity.com/paper/2409.13513/) (2024)

## Abstract (arXiv)

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.