Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning


Creative Commons License

CİNBİŞ R. G. , Verbeek J., Schmid C.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, cilt.39, ss.189-203, 2017 (SCI İndekslerine Giren Dergi) identifier identifier identifier

  • Cilt numarası: 39 Konu: 1
  • Basım Tarihi: 2017
  • Doi Numarası: 10.1109/tpami.2016.2535231
  • Dergi Adı: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
  • Sayfa Sayıları: ss.189-203

Özet

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 using high-dimensional representations, such as Fisher vectors and convolutional neural network features. We also propose a window refinement method, which improves the localization accuracy by incorporating an objectness prior. We present a detailed experimental evaluation using the PASCALVOC 2007 dataset, which verifies the effectiveness of our approach.