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 $$\kappa $$ exemplar-based nearest neighbors ( $$\kappa \text {ENN}$$ ) to assist automatically the classifier. A pretrained convolutional neural network is used to perform $$\kappa \text {ENN}$$ 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 labor-saving (human assistance percentages of less than $$20\%$$ ). As a by-product, we demonstrate that WiLFs also perform semiautomatic annotation during learning, as while the classifier is being computed, WiLFs are discovering faces instances in input images which are used subsequently for training online the classifier. The advantages of our approach are demonstrated in synthetic and publicly available databases, showing comparable detection rates as offline approaches that require larger amounts of handmade training data.