Unsupervised Deep Cross-modality Spectral Hashing

TL;DR

This paper introduces Deep Cross-modality Spectral Hashing (DCSH), an unsupervised framework that learns binary hash codes for efficient cross-modal retrieval by combining spectral embedding and deep learning techniques.

Contribution

The paper proposes a novel two-step unsupervised hashing framework that integrates spectral embedding with deep neural networks for cross-modal retrieval.

Findings

DCSH outperforms existing methods on benchmark datasets.

The spectral embedding effectively captures local and cross-modal structures.

Deep learning models accurately map data to binary codes.

Abstract

This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval. The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2) hashing function learning. In the first step, we propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations. While the former is capable of well preserving the local structure of each modality, the latter reveals the hidden patterns from all modalities. In the second step, to learn mapping functions from informative data inputs (images and word embeddings) to binary codes obtained from the first step, we leverage the powerful CNN for images and propose a CNN-based deep architecture to learn text modality. Quantitative evaluations on three standard benchmark datasets demonstrate that the proposed DCSH method consistently outperforms other state-of-the-art methods.