# One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network

## TL;DR

This paper introduces a domain adaptive hashing framework using intersectant generative adversarial networks to improve image recognition and retrieval across different domains, achieving superior results on benchmark datasets.

## Contribution

It proposes a novel end-to-end domain adaptive hashing method that aligns two domains in a shared semantic space with intersectant GANs, enhancing cross-domain performance.

## Key findings

- Outperforms state-of-the-art methods on four benchmark datasets.
- Effectively reduces domain disparity and improves hash code discriminability.
- Enhances image retrieval and recognition accuracy across domains.

## Abstract

With the recent explosive increase of digital data, image recognition and retrieval become a critical practical application. Hashing is an effective solution to this problem, due to its low storage requirement and high query speed. However, most of past works focus on hashing in a single (source) domain. Thus, the learned hash function may not adapt well in a new (target) domain that has a large distributional difference with the source domain. In this paper, we explore an end-to-end domain adaptive learning framework that simultaneously and precisely generates discriminative hash codes and classifies target domain images. Our method encodes two domains images into a semantic common space, followed by two independent generative adversarial networks arming at crosswise reconstructing two domains' images, reducing domain disparity and improving alignment in the shared space. We evaluate our framework on {four} public benchmark datasets, all of which show that our method is superior to the other state-of-the-art methods on the tasks of object recognition and image retrieval.