Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2016

Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

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 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 PASCAL VOC 2007 dataset, which verifies the effectiveness of our approach.
Fichier principal
Vignette du fichier
paper.pdf (4) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01123482 , version 1 (04-03-2015)
hal-01123482 , version 2 (03-09-2015)
hal-01123482 , version 3 (22-02-2016)

Identifiers

Cite

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016. ⟨hal-01123482v2⟩
1231 View
1651 Download

Altmetric

Share

More