Abstract

We present a method for discovering and exploiting object specific deep features and use face detection as a case study. Motivated by the observation that certain convolutional channels of a Convolutional Neural Network (CNN) exhibit object specific responses, 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.

Overview

Results