Multi-fold MIL Training for Weakly Supervised Object Localization

Ramazan Gokberk Cinbis 1 Jakob Verbeek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download


https://hal.inria.fr/hal-00975746
Contributor : Thoth Team <>
Submitted on : Wednesday, April 9, 2014 - 9:45:24 AM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on : Wednesday, July 9, 2014 - 11:25:55 AM

Files

paper.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Multi-fold MIL Training for Weakly Supervised Object Localization. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, United States. pp.2409-2416, ⟨10.1109/CVPR.2014.309⟩. ⟨hal-00975746⟩

Share

Metrics

Record views

1587

Files downloads

5817