Weakly supervised object localization with multi-fold multiple instance learning
Author
Cinbis, R. G.
Verbeek, J.
Schmid, C.
Date
2017Source Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
Print ISSN
0162-8828
Publisher
IEEE Computer Society
Volume
39
Issue
1
Pages
189 - 203
Language
English
Type
ArticleItem Usage Stats
149
views
views
190
downloads
downloads
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. © 2016 IEEE.
Keywords
Object detectionWeakly supervised learning
Computer vision
Iterative methods
Learning systems
Location
Locks (fasteners)
Neural networks
Supervised learning
Convolutional neural network
Experimental evaluation
Localization accuracy
Multiple instance learning
Object localization
Refinement methods
Supervised trainings
Object recognition
Permalink
http://hdl.handle.net/11693/37100Published Version (Please cite this version)
http://dx.doi.org/10.1109/TPAMI.2016.2535231Collections
Related items
Showing items related by title, author, creator and subject.
-
Adaptive ensemble learning with confidence bounds for personalized diagnosis
Tekin, Cem; Yoon, J.; Van Der Schaar, M. (AAAI Press, 2016)With the advances in the field of medical informatics, automated clinical decision support systems are becoming the de facto standard in personalized diagnosis. In order to establish high accuracy and confidence in ... -
The effect of uncertainty on learning in game-like environments
Ozcelik, E.; Cagiltay, N. E.; Ozcelik, N. S. (Pergamon Press, 2013)Considering the role of games for educational purposes, there has an increase in interest among educators in applying strategies used in popular games to create more engaging learning environments. Learning is more fun and ... -
Big-data streaming applications scheduling based on staged multi-armed bandits
Kanoun, K.; Tekin, C.; Atienza, D.; Van Der Schaar, M. (Institute of Electrical and Electronics Engineers, 2016)Several techniques have been recently proposed to adapt Big-Data streaming applications to existing many core platforms. Among these techniques, online reinforcement learning methods have been proposed that learn how to ...