Collaborative Learning for Extremely Low Bit Asymmetric Hashing
Authors:
- Yadan LuoYLYadan Luo
- Yang LiYLYang Li
- Fumin ShenFSFumin Shen
- Yang YangYYYang Yang
- Peng CuiPeng Cui
- Zi HuangZHZi Huang
Preprint
Abstract
Extremely low bit (e.g., 4-bit) hashing is in high demand for retrieval and network compression, yet it could hardly guarantee a manageable convergence or performance due to its severe information loss and shrink of discrete solution space. In this paper, we propose a novel Collaborative Learning strategy for high-quality low-bit deep hashing. The core idea is to distill bit-specific representations for low-bit codes with a group of hashing learners, where hash codes of various length actively interact by sharing and accumulating knowledge. To achieve that, an asymmetric hashing framework with two variants of multi-head embedding structures is derived, termed as Multi-head Asymmetric Hashing (MAH), leading to great efficiency of training and querying. Multiple views from different embedding heads provide supplementary guidance as well as regularization for extremely low bit hashing, hence making convergence faster and more stable. Extensive experiments on three benchmark datasets have been conducted to verify the superiority of the proposed MAH, and show that 8-bit hash codes generated by MAH achieve 94.4% of MAP score, which significantly surpasses the performance of 48-bit codes by the state-of-the-arts for image retrieval.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Robust discrete code modeling for supervised hashingPattern Recognition, 2018
- HashNet: Deep Learning to Hash by Continuation2017
- Asymmetric sparse hashing2017
- Attribute hashing for zero-shot image retrieval2017
- Fast Person Re-identification via Cross-Camera Semantic Binary Transformation2017
- Part-Based Deep Hashing for Large-Scale Person Re-IdentificationIEEE Transactions on Image Processing, 2017
- A Fast Optimization Method for General Binary Code LearningIEEE Transactions on Image Processing, 2016
- Deep Residual Learning for Image Recognition2016
- Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-IdentificationIEEE Transactions on Image Processing, 2015
- Supervised Discrete Hashing2015