Collaborative Learning For Extremely Low Bit Asymmetric Hashing

Abstract

Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression. Nevertheless, existing approaches could hardly guarantee a satisfactory performance with the extremely low-bit (e.g., 4-bit) hash codes due to the severe information loss and the shrink of the discrete solution space. In this paper, we propose a novel \textit\{Collaborative Learning\} strategy that is tailored for generating high-quality low-bit hash codes. The core idea is to jointly distill bit-specific and informative representations for a group of pre-defined code lengths. The learning of short hash codes among the group can benefit from the manifold shared with other long codes, where multiple views from different hash codes provide the supplementary guidance and regularization, making the convergence faster and more stable. To achieve that, an asymmetric hashing framework with two variants of multi-head embedding structures is derived, termed as Mult

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keyluo2018collaborative

Related papers

• Scalable Discrete Supervised Hash Learning With Asymmetric Matrix Factorization (2016)4.52
• Simultaneous Feature Aggregating And Hashing For Compact Binary Code Learning (2019)9.92
• Dual Asymmetric Deep Hashing Learning (2018)9.03
• A Lower Bound Of Hash Codes' Performance (2022)1.56
• Deep Hashing: A Joint Approach For Image Signature Learning (2016)5.24
• Mutual Learning For Hashing: Unlocking Strong Hash Functions From Weak Supervision (2025)0.00
• Compact Hash Code Learning With Binary Deep Neural Network (2017)9.03
• Structured Learning Of Binary Codes With Column Generation (2016)0.00