To Project More or to Quantize More: Minimize Reconstruction Bias for Learning Compact Binary Codes

Wang, Zhe; Duan, Ling-Yu; Yuan, Junsong; Huang, Tiejun; Gao, Wen

To Project More or to Quantize More: Minimize Reconstruction Bias for Learning Compact Binary Codes

Zhe Wang, Ling-Yu Duan, Junsong Yuan, Tiejun Huang, Wen Gao

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2181-2187.

Abstract

We present a novel approach called Minimal Reconstruction Bias Hashing (MRH) to learn similarity preserving binary codes that jointly optimize both projection and quantization stages. Our work tackles an important problem of how to elegantly connect optimizing projection with optimizing quantization, and to maximize the complementary effects of two stages. Distinct from previous works, MRH can adaptively adjust the projection dimensionality to balance the information loss between projection and quantization. It is formulated as a problem of minimizing reconstruction bias of compressed signals. Extensive experiment results have shown the proposed MRH significantly outperforms a variety of state-of-the-art methods over several widely used benchmarks.

Zhe Wang, Ling-Yu Duan, Junsong Yuan, Tiejun Huang, and Wen Gao. 2016. To Project More or to Quantize More: Minimize Reconstruction Bias for Learning Compact Binary Codes. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2181–2187. https://ijcai.org/proceedings/2016/311

@inproceedings{ijcai2016p311,
  title     = {To Project More or to Quantize More: Minimize Reconstruction Bias for Learning Compact Binary Codes},
  author    = {Wang, Zhe and Duan, Ling-Yu and Yuan, Junsong and Huang, Tiejun and Gao, Wen},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {2181--2187},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/311},
}

TY  - CPAPER
TI  - To Project More or to Quantize More: Minimize Reconstruction Bias for Learning Compact Binary Codes
AU  - Wang, Zhe
AU  - Duan, Ling-Yu
AU  - Yuan, Junsong
AU  - Huang, Tiejun
AU  - Gao, Wen
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 2181
EP  - 2187
UR  - https://ijcai.org/proceedings/2016/311
ER  -