One-bit Semantic Hashing: Towards Resource-Efficient Hashing Model with Binary Neural Network

Liyang He, Zhenya Huang, Chenglong Liu, Rui Li, Runze Wu, Qi Liu, Enhong Chen

Abstract: Deep Hashing (DH) has emerged as an indispensable technique for fast image search in recent years. However, using full-precision Convolutional Neural Networks (CNN) in DH makes it challenging to deploy on devices with limited resources. To deploy DH on resource-limited devices, the Binary Neural Network (BNN) offers a solution that significantly reduces computations and parameters compared to CNN. Unfortunately, applying BNN directly to DH will lead to huge performance degradation. To tackle this problem, we first conducted extensive experiments and discovered that the center-based method provides a fundamental guarantee for BNN-DH performance. Subsequently, we delved deeper into the impact of BNNs on center-based methods and revealed two key insights. First, we find reducing the distance between hash codes and hash centers is challenging for BNN-DH compared to CNN-based DH. This can be attributed to the limited representation capability of BNN. Second, the evolution of hash code aggregation undergoes two stages in BNN-DH, which is different from CNN-based DH. Thus, we need to take into account the changing trends in code aggregation at different stages. Based on these findings, we designed a strong and general method called One-bit Deep Hashing (ODH). First, ODH incorporates a semantic self-adaptive hash center module to address the problem of hash codes inadequately converging to their hash centers. Then, it employs a novel two-stage training method to consider the evolution of hash code aggregation. Finally, extensive experiments on two datasets demonstrate that ODH can achieve significant superiority over other BNN-DH models. The code for ODH is available at https://anonymous.4open.science/r/OSH-1730.

Primary Subject Area: [Systems] Data Systems Management and Indexing

Relevance To Conference: Deep Hashing is an important technique for fast image search in the multimedia community. However, the use of full-precision CNN in current deep hashing makes it challenging to deploy on devices with limited resources. We propose a strong and general method called One-bit Semantic Hashing (OSH) to solve this problem. Our model can adapt to existing BNN frameworks, thereby overcoming this dilemma.

Submission Number: 4311