Probabilistic Elastic Part Model for Unsupervised Face Detector Adaptation

Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, Jianchao Yang; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 793-800

Abstract


We propose an unsupervised detector adaptation algorithm to adapt any offline trained face detector to a specific collection of images, and hence achieve better accuracy. The core of our detector adaptation algorithm is a probabilistic elastic part (PEP) model, which is offline trained with a set of face examples. It produces a statisticallyaligned part based face representation, namely the PEP representation. To adapt a general face detector to a collection of images, we compute the PEP representations of the candidate detections from the general face detector, and then train a discriminative classifier with the top positives and negatives. Then we re-rank all the candidate detections with this classifier. This way, a face detector tailored to the statistics of the specific image collection is adapted from the original detector. We present extensive results on three datasets with two state-of-the-art face detectors. The significant improvement of detection accuracy over these stateof-the-art face detectors strongly demonstrates the efficacy of the proposed face detector adaptation algorithm.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2013_ICCV,
author = {Li, Haoxiang and Hua, Gang and Lin, Zhe and Brandt, Jonathan and Yang, Jianchao},
title = {Probabilistic Elastic Part Model for Unsupervised Face Detector Adaptation},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}