Zero-Shot Hashing via Transferring Supervised Knowledge

Abstract

Hashing has shown its efficiency and effectiveness in facilitating large-scale multimedia applications. Supervised knowledge e.g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the quality of hash codes and hash functions. However, confronted with the rapid growth of newly-emerging concepts and multimedia data on the Web, existing supervised hashing approaches may easily suffer from the scarcity and validity of supervised information due to the expensive cost of manual labelling. In this paper, we propose a novel hashing scheme, termed \emph{zero-shot hashing} (ZSH), which compresses images of "unseen" categories to binary codes with hash functions learned from limited training data of "seen" categories. Specifically, we project independent data labels i.e. 0/1-form label vectors) into semantic embedding space, where semantic relationships among all the labels can be precisely characterized and thus seen supervised knowledge can be transferred to unseen classes. Moreover, in order to cope with the semantic shift problem, we rotate the embedded space to more suitably align the embedded semantics with the low-level visual feature space, thereby alleviating the influence of semantic gap. In the meantime, to exert positive effects on learning high-quality hash functions, we further propose to preserve local structural property and discrete nature in binary codes. Besides, we develop an efficient alternating algorithm to solve the ZSH model. Extensive experiments conducted on various real-life datasets show the superior zero-shot image retrieval performance of ZSH as compared to several state-of-the-art hashing methods.

11 pages

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Supervised Discrete Hashing

Cited by in corpus (15)

• Zero-Shot Sketch-Image Hashing
• Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
• Embarrassingly Simple Binary Representation Learning
• Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches
• Collaborative Learning for Extremely Low Bit Asymmetric Hashing
• Alleviating Feature Confusion for Generative Zero-shot Learning
• Domain-Specific Embedding Network for Zero-Shot Recognition
• Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining
• Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
• Hashing in the Zero Shot Framework with Domain Adaptation
• Interactive Search and Exploration in Online Discussion Forums Using Multimodal Embeddings
• Optimal Projection Guided Transfer Hashing for Image Retrieval
• Weakly-Supervised Online Hashing
• Mitigating Generation Shifts for Generalized Zero-Shot Learning
• Deep Collaborative Discrete Hashing with Semantic-Invariant Structure