Simultaneous object detection and ranking with weak supervision

Conference item

A standard approach to learning object category detectors is to provide strong supervision in the form of a region of interest (ROI) specifying each instance of the object in the training images. In this work are goal is to learn from heterogeneous labels, in which some images are only weakly supervised, specifying only the presence or absence of the object or a weak indication of object location, whilst others are fully annotated. To this end we develop a discriminative learning approach and make two contributions: (i) we propose a structured output formulation for weakly annotated images where full annotations are treated as latent variables; and (ii) we propose to optimize a ranking objective function, allowing our method to more effectively use negatively labeled images to improve detection average precision performance. The method is demonstrated on the benchmark INRIA pedestrian detection dataset of Dalal and Triggs and the PASCAL VOC dataset, and it is shown that for a significant proportion of weakly supervised images the performance achieved is very similar to the fully supervised (state of the art) results.

Authors: Blaschko, MB; Vedaldi, A; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Curran Associates
• Host title: Advances in Neural Information Processing Systems 23
• Volume: 1
• Pages: 235-243
• Publication date: 2011-06-01
• Acceptance date: 2010-08-31
• Event title: 24th Annual Conference on Neural Information Processing Systems 2010 (NIPS 2010)
• Event location: Vancouver, BC, Canada
• Event website: https://nips.cc/Conferences/2010
• Event start date: 2010-12-06
• Event end date: 2010-12-09
• ISSN: 1049-5258
• ISBN: 9781617823800
• Language: English