Hashing in the Zero Shot Framework with Domain Adaptation

TL;DR

This paper introduces a zero-shot hashing framework with domain adaptation that effectively encodes unseen class images into binary codes, improving retrieval performance by addressing domain shift and quantization errors.

Contribution

It proposes a novel hashing algorithm that combines max-margin classifiers with unsupervised domain adaptation for zero-shot image retrieval.

Findings

Domain adaptation improves hash function quality.

The method outperforms state-of-the-art hashing techniques.

Effective encoding of unseen classes demonstrated.

Abstract

Techniques to learn hash codes which can store and retrieve large dimensional multimedia data efficiently have attracted broad research interests in the recent years. With rapid explosion of newly emerged concepts and online data, existing supervised hashing algorithms suffer from the problem of scarcity of ground truth annotations due to the high cost of obtaining manual annotations. Therefore, we propose an algorithm to learn a hash function from training images belonging to `seen' classes which can efficiently encode images of `unseen' classes to binary codes. Specifically, we project the image features from visual space and semantic features from semantic space into a common Hamming subspace. Earlier works to generate hash codes have tried to relax the discrete constraints on hash codes and solve the continuous optimization problem. However, it often leads to quantization errors. In this work, we use the max-margin classifier to learn an efficient hash function. To address the concern of domain-shift which may arise due to the introduction of new classes, we also introduce an unsupervised domain adaptation model in the proposed hashing framework. Results on the three datasets show the advantage of using domain adaptation in learning a high-quality hash function and superiority of our method for the task of image retrieval performance as compared to several state-of-the-art hashing methods.