Weakly Supervised Object Detection with Posterior Regularization

Abstract

© 2014. The copyright of this document resides with its authors. This paper focuses on the problem of object detection when the annotation at training time is restricted to presence or absence of object instances at image level. We present a method based on features extracted from a Convolutional Neural Network and latent SVM that can represent and exploit the presence of multiple object instances in an image. Moreover, the detection of the object instances in the image is improved by incorporating in the learning procedure additional constraints that represent domain-specific knowledge such as symmetry and mutual exclusion. We show that the proposed method outperforms the state-of-the-art in weakly-supervised object detection and object classification on the Pascal VOC 2007 dataset.