Object specific deep feature and its application to face detection

We present a method for exploiting object specific deep features and use face detection as a case study. We seek to discover and exploit the convolutional channels of a CNN in which neurons are activated by the presence of specific objects in the input image. A method for explicitly fine-tuning a pre-trained CNN to induce an object specific channel (OSC) and systematically identifying it for the human face object has been developed. Building on the basic OSC features, we introduce a multi-scale approach to constructing robust face heatmaps for rapidly filtering out non-face regions thus significantly improving search efficiency for face detection in unconstrained settings. We show that multi-scale OSC can be used to develop simple and compact face detectors with state of the art performance.