ABSTRACT
This paper addresses the problem of producing very compact representation of a face image for large-scale face search and analysis tasks. In tradition, the compactness of face representation is achieved by a dimension reduction step after representation extraction. However, the dimension reduction usually degrades the discriminative ability of the original representation drastically. In this paper, we present a deep learning framework which optimizes the compactness and discriminative ability jointly. The learnt representation can be as compact as 32 bit (same as the int32) and still produce highly discriminative performance (91.4% on LFW benchmark). Based on the extreme compactness, we show that traditional face analysis tasks (e.g. gender analysis) can be effectively solved by a Look-Up-Table approach given a large-scale face data set.
- Y. Bengio. Learning deep architectures for ai. FTML, 2(1):1--127, 2009. Google ScholarDigital Library
- D. Chen, X. Cao, F. Wen, and J. Sun. Blessing of dimensionality: High-dimensional feature and its efficient compression for face verification. In CVPR, pages 3025--3032. IEEE, 2013. Google ScholarDigital Library
- H. Fan, Z. Cao, Y. Jiang, Q. Yin, and C. Doudou. Learning deep face representation. Technical report, Megvii. Inc, Beijing, March 2014.Google Scholar
- Y. Gong and S. Lazebnik. Iterative quantization: A procrustean approach to learning binary codes. In CVPR, pages 817--824. IEEE, 2011. Google ScholarDigital Library
- G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504--507, 2006.Google ScholarCross Ref
- G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07--49, University of Massachusetts, Amherst, October 2007.Google Scholar
- K. Jarrett, K. Kavukcuoglu, M. Ranzato, and Y. LeCun. What is the best multi-stage architecture for object recognition? In ICCV, pages 2146--2153. IEEE, 2009.Google ScholarCross Ref
- N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attribute and simile classifiers for face verification. In ICCV, pages 365--372. IEEE, 2009.Google ScholarCross Ref
- Y. Taigman and L. Wolf. Leveraging billions of faces to overcome performance barriers in unconstrained face recognition. arXiv preprint arXiv:1108.1122, 2011.Google Scholar
- Q. Yin, X. Tang, and J. Sun. An associate-predict model for face recognition. In CVPR, pages 497--504. IEEE, 2011. Google ScholarDigital Library
- L. Zhang, Y. Zhang, J. Tang, X. Gu, J. Li, and Q. Tian. Topology preserving hashing for similarity search. In ACMM, pages 123--132. ACM, 2013. Google ScholarDigital Library
Index Terms
- Learning Compact Face Representation: Packing a Face into an int32
Recommendations
Deep compact discriminative representation for unconstrained face recognition
AbstractConvolutional Neural Network has been widely used in pattern recognition community, especially face recognition. Loss function, as a supervisory signal to learn a CNN model, plays an important role in obtaining the desired facial ...
Highlights- Two losses are for compact and discriminative deep face features.
- The intra-...
Robust face recognition based on dynamic rank representation
Robust face recognition is an active topic in computer vision, while face occlusion is one of the most challenging problems for robust face recognition algorithm. The latest research on low-rank representation demonstrated its high efficiency to ...
Pose and illumination variable face recognition via sparse representation and illumination dictionary
This paper addresses the problem of face recognition under pose and illumination variations, and proposes a novel algorithm inspired by the idea of sparse representation (SR). In order to make the SR early designed for the pose-invariant face ...
Comments