Online learning and detection of faces with low human supervision

Abstract

We present an efficient, online, and interactive approach for computing a classifier, called Wild Lady Ferns (WiLFs), for face learning and detection using small human supervision. More precisely, on the one hand, WiLFs combine online boosting and extremely randomized trees (Random Ferns) to compute progressively an efficient and discriminative classifier. On the other hand, WiLFs use an interactive human-machine approach that combines two complementary learning strategies to reduce considerably the degree of human supervision during learning. While the first strategy corresponds to query-by-boosting active learning, that requests human assistance over difficult samples in function of the classifier confidence, the second strategy refers to a memory-based learning which uses κ Exemplar-based Nearest Neighbors (κENN) to assist automatically the classifier. A pre-trained Convolutional Neural Network (CNN) is used to perform κENN with high-level feature descriptors. The proposed approach is therefore fast (WilFs run in 1 FPS using a code not fully optimized), accurate (we obtain detection rates over 82% in complex datasets), and laborsaving (human assistance percentages of less than 20%). As a byproduct, we demonstrate that WiLFs also perform semi-automatic annotation during learning, as while the classifier is being computed, WiLFs are discovering faces instances in input images which are used subsequently for