Learning A Deep ℓ∞ Encoder for Hashing

Wang, Zhangyang; Yang, Yingzhen; Chang, Shiyu; Ling, Qing; Huang, Thomas S.

Learning A Deep ℓ∞ Encoder for Hashing

Zhangyang Wang, Yingzhen Yang, Shiyu Chang, Qing Ling, Thomas S. Huang

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2174-2179.

Abstract

We investigate the L-infinity constrained representation which demonstrates robustness to quantization errors, utilizing the tool of deep learning. Based on the Alternating Direction Method of Multipliers (ADMM), we formulate the original convex minimization problem as a feed-forward neural network, named Deep L-infinity Encoder, by introducing the novel Bounded Linear Unit (BLU) neuron and modeling the Lagrange multipliers as network biases. Such a structural prior acts as an effective network regularization, and facilitates the model initialization. We then investigate the effective use of the proposed model in the application of hashing, by coupling the proposed encoders under a supervised pairwise loss, to develop a Deep Siamese L-infinity Network, which can be optimized from end to end. Extensive experiments demonstrate the impressive performances of the proposed model. We also provide an in-depth analysis of its behaviors against the competitors.

Zhangyang Wang, Yingzhen Yang, Shiyu Chang, Qing Ling, and Thomas S. Huang. 2016. Learning A Deep ℓ∞ Encoder for Hashing. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2174–2179. https://ijcai.org/proceedings/2016/310

@inproceedings{ijcai2016p310,
  title     = {Learning A Deep ℓ∞ Encoder for Hashing},
  author    = {Wang, Zhangyang and Yang, Yingzhen and Chang, Shiyu and Ling, Qing and Huang, Thomas S.},
  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     = {2174--2179},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/310},
}

TY  - CPAPER
TI  - Learning A Deep ℓ∞ Encoder for Hashing
AU  - Wang, Zhangyang
AU  - Yang, Yingzhen
AU  - Chang, Shiyu
AU  - Ling, Qing
AU  - Huang, Thomas S.
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  - 2174
EP  - 2179
UR  - https://ijcai.org/proceedings/2016/310
ER  -