Unsupervised Deep Cross-modality Spectral Hashing

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.

arXiv commentAccepted to IEEE Transaction on Image Processing (TIP) Add Acknowledgement

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Estimation of Word Representations in Vector Space
• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
• Fast Supervised Hashing with Decision Trees for High-Dimensional Data
• Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
• Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
• Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning