Multi-label Contractive Hashing Method for Face Attributes Retrieval
ZHAO Xuan, TAN Xiaoyang, SONG Ge
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106 Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210093
Abstract：Hashing methods possess advantages of low storage cost and fast query speed. However, most of the current hashing methods are designed to handle simple binary similarity rather than the complex multilevel semantic structure of the images associated with multiple labels. In this paper, a multi-label contractive hashing method(MLCH) is proposed to preserve the multilevel semantic similarity of multi-label images. In particular, the supervising information of attributes is proposed to help the training of the model and adopt an optimized selection algorithm to select training samples. Meanwhile, a contractive constrain term is added to the loss function to improve the quality of the generated binary codes. The proposed approach is evaluated on CelebA and PubFig databases, and the experimental results demonstrate its superiority over several state-of-the-art hashing methods on the task of large-scale image retrieval.
[1] GIONIS A, INDYK P, MOTWANI R. Similarity Search in High Dimensions via Hashing // Proc of the 25th International Conference on Very Large Data Bases. San Francisco, USA: Morgan Kaufmann Publishers, 2000: 518-529. [2] LIU W, WANG J, KUMAR S, et al. Hashing with Graphs[C/OL]. [2017-03-21]. http://www.icml-2011.org/papers/6_icmlpaper.pdf. [3] SONG J K, YANG Y, YANG Y, et al. Inter-Media Hashing for Large-Scale Retrieval from Heterogeneous Data Sources // Proc of the ACM SIGMOD International Conference on Management of Data. New York, USA: ACM, 2013: 785-796. [4] WANG J, CHANG S F, KUMAR S. Semi-supervised Hashing for Large-Scale Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(12): 2393-2406. [5] SLANEY M, CASEY M. Locality-Sensitive Hashing for Finding Nearest Neighbors. IEEE Signal Processing Magazine, 2008, 25(2): 128-131. [6] WEISS Y, TORRALBA A, FERGUS R. Spectral Hashing[C/OL]. [2017-03-21]. http://people.csail.mit.edu/torralba/publications/spectralhashing.pdf. [7] GONG Y C, LAZEBNIK S. Iterative Quantization: A Procrustean approach to Learning Binary Codes // Proc of the 24th IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 817-824. [8] ZHANG P C, ZHANG W, LI W J, et al. Supervised Hashing with Latent Factor Models // Proc of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2014: 173-182. [9] NOROUZI M, FLEET D J, SALAKHUTDINOV R. Hamming Distance Metric Learning // Proc of the 25th International Conference on Neural Information Processing Systems. New York, USA: ACM, 2012, II: 1061-1069. [10] SALAKHUTDINOV R, HINTON G. Semantic Hashing. International Journal of Approximate Reasoning, 2009, 50(7): 969-978. [11] SHEN F M, SHEN C H, LIU W, et al. Supervised Discrete Ha-shing // Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2015: 37-45. [12] HARDOON D R, SZEDMAK S R, SHAWE-TAYLOR J R. Canonical Correlation Analysis: An Overview with Application to Learning Methods. Neural Computation, 2004, 16(12): 2639-2664. [13] LI Y, WANG R P, LIU H M, et al. Two Birds, One Stone: Jointly Learning Binary Code for Large-Scale Face Image Retrieval and Attributes Prediction // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 3819-3827. [14] ZHONG Y, SULLIVAN J, LI H B. Face Attribute Prediction Using Off-the-Shelf CNN Features // Proc of the International Conference on Biometrics. Washington, USA: IEEE, 2016. DOI: 10.1109.ICB.2016.7550092. [15] ZHONG Y, SULLIVAN J, LI H B. Leveraging Mid-Level Deep Representations for Predicting Face Attributes in the Wild // Proc of the IEEE International Conference on Image Processing. Washington, USA: IEEE, 2016: 3239-3243. [16] KUMAR N, BELHUMEUR P, NAYAR S. FaceTracer: A Search Engine for Large Collections of Images with Faces // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer-Verlag, 2008: 340-353. [17] LIU H Y, TIAN Y H, WANG Y W, et al. Deep Relative Distance Learning: Tell the Difference between Similar Vehicles // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 2167-2175. [18] RIFAI S, VINCENT P, MULLER X, et al. Contractive Auto-Encoders: Explicit Invariance During Feature Extraction // Proc of the International Conference on Machine Learning. New York, USA: ACM, 2011: 833-840. [19] LIU Z W, LUO P, WANG X G, et al. Deep Learning Face Attri-butes in the Wild // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 3730-3738. [20] KUMAR N, BERG A C, BELHUMEUR P N, et al. Attribute and Simile Classifiers for Face Verification // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2010: 365-372. [21] LIU W, WANG J, JI R R, et al. Supervised Hashing with Kernels // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 2074-2081. [22] ZHAO F, HUANG Y Z, WANG L, et al. Deep Semantic Ranking Based Hashing for Multi-label Image Retrieval // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 1556-1564. [23] SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J/OL]. [2017-03-21]. https://arxiv.org/pdf/1409.1556.pdf.
2017, Vol. 30 
