Deep Unsupervised Hashing by Distilled Smooth Guidance

TL;DR

This paper introduces a novel deep unsupervised hashing method called Distilled Smooth Guidance (DSG) that effectively learns similarity signals and smooth confidence signals, improving search performance without labeled data.

Contribution

The paper proposes DSG, a deep unsupervised hashing approach that distills reliable similarity signals and smooth confidence information to enhance hashing accuracy.

Findings

DSG outperforms state-of-the-art methods on benchmark datasets.

The method effectively utilizes local structures and clustering for signal distillation.

Extensive experiments validate the robustness and superiority of DSG.

Abstract

Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency. Deep supervised hashing methods are not widely used because of the lack of labeled data, especially when the domain is transferred. Meanwhile, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable similarity signals. To tackle this problem, we propose a novel deep unsupervised hashing method, namely Distilled Smooth Guidance (DSG), which can learn a distilled dataset consisting of similarity signals as well as smooth confidence signals. To be specific, we obtain the similarity confidence weights based on the initial noisy similarity signals learned from local structures and construct a priority loss function for smooth similarity-preserving learning. Besides, global information based on clustering is utilized to distill the image pairs by removing contradictory similarity signals. Extensive experiments on three widely used benchmark datasets show that the proposed DSG consistently outperforms the state-of-the-art search methods.