Journal
IEEE ACCESS
Volume 5, Issue -, Pages 23157-23165Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2017.2749331
Keywords
Fisher vector; face recognition; dimensional reduction; hashing; convolutional activations
Categories
Funding
- National Natural Science Foundation of China [61471048, 61573068, 61375031]
- Beijing Nova Program [Z161100004916088]
- Fundamental Research Funds for the Central Universities [2014ZD03-01]
Ask authors/readers for more resources
One major topic for robust face recognition could be the efficient encoding of facial descriptors. Among various encoders, Fisher vector (FV) is one of the probabilistic methods that yield promising results. However, its huge representation is fairly forbidding. In this paper, we present approaches to efficiently compress FV and retain its robustness. First, we put forward a new Compact FV (CFV) descriptor. The CFV is obtained by zeroing out small posteriors, calculating first-order statistics and reweighting its elements properly. Second, in light of Iterative Quantization (ITQ) scheme, we present a Generalized ITQ (GITQ) method to binarize our CFV. Finally, we apply our CFV and GITQ to encode convolutional activations of convolutional neural networks. We evaluate our methods on FERET, LFW, AR, and FRGC 2.0 datasets, and our experiments reveal the advantage of such a framework.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available