Training Object Class Detectors with Click Supervision
Authors:
- Dim P. PapadopoulosDPDim P. Papadopoulos
- Jasper R. R. UijlingsJUJasper R. R. Uijlings
- Frank KellerFKFrank Keller
- Vittorio FerrariVFVittorio Ferrari
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 180-189
Abstract
Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing center-click annotations: we ask annotators to click on the center of an imaginary bounding box which tightly encloses the object instance. We then incorporate these clicks into existing Multiple Instance Learning techniques for weakly supervised object localization, to jointly localize object bounding boxes over all training images. Extensive experiments on PASCAL VOC 2007 and MS COCO show that: (1) our scheme delivers high-quality detectors, performing substantially better than those produced by weakly supervised techniques, with a modest extra annotation effort, (2) these detectors in fact perform in a range close to those trained from manually drawn bounding boxes, (3) as the center-click task is very fast, our scheme reduces total annotation time by 9x to 18x.Keywords
All Related Versions
This publication has 58 references indexed in Scilit:
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Efficiently Scaling up Crowdsourced Video AnnotationInternational Journal of Computer Vision, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- A New Look at Infant PointingChild Development, 2007
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007
- Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search.Psychological Review, 2006
- Towards a standard for pointing device evaluation, perspectives on 27 years of Fitts’ law research in HCIInternational Journal of Human-Computer Studies, 2004
- Executive control of cognitive processes in task switching.Journal of Experimental Psychology: Human Perception and Performance, 2001
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997