Unifying Specialist Image Embedding into Universal Image Embedding

by   Yang Feng, et al.

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.


page 1

page 2

page 3

page 4


Universal Model for Multi-Domain Medical Image Retrieval

Medical Image Retrieval (MIR) helps doctors quickly find similar patient...

Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations

Fine-grained and instance-level recognition methods are commonly trained...

Learning a Deep Embedding Model for Zero-Shot Learning

Zero-shot learning (ZSL) models rely on learning a joint embedding space...

Domain-Specific Embedding Network for Zero-Shot Recognition

Zero-Shot Learning (ZSL) seeks to recognize a sample from either seen or...

Semantic Diversity Learning for Zero-Shot Multi-label Classification

Training a neural network model for recognizing multiple labels associat...

Scaling ASR Improves Zero and Few Shot Learning

With 4.5 million hours of English speech from 10 different sources acros...

Universal Horn Sentences and the Joint Embedding Property

The finite models of a universal sentence Φ are the age of a structure i...

Please sign up or login with your details

Forgot password? Click here to reset