Multi-fold MIL Training for Weakly Supervised Object Localization


Creative Commons License

Cinbiş R. G., Verbeek J., Schmid C.

27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Ohio, United States Of America, 23 - 28 June 2014, pp.2409-2416 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/cvpr.2014.309
  • City: Ohio
  • Country: United States Of America
  • Page Numbers: pp.2409-2416
  • Middle East Technical University Affiliated: Yes

Abstract

Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when high-dimensional representations, such as the Fisher vectors, are used. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset. Compared to state-of-the-art weakly supervised detectors, our approach better localizes objects in the training images, which translates into improved detection performance.