Active Image Segmentation Propagation
Authors:
- Suyog Dutt JainSJSuyog Dutt Jain
- Kristen GraumanKGKristen Grauman
- 12 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2864-2873
Abstract
We propose a semi-automatic method to obtain foreground object masks for a large set of related images. We develop a stagewise active approach to propagation: in each stage, we actively determine the images that appear most valuable for human annotation, then revise the foreground estimates in all unlabeled images accordingly. In order to identify images that, once annotated, will propagate well to other examples, we introduce an active selection procedure that operates on the joint segmentation graph over all images. It prioritizes human intervention for those images that are uncertain and influential in the graph, while also mutually diverse. We apply our method to obtain foreground masks for over 1 million images. Our method yields state-of-the-art accuracy on the ImageNet and MIT Object Discovery datasets, and it focuses human attention more effectively than existing propagation strategies.Keywords
This publication has 32 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- ImageNet Auto-Annotation with Segmentation PropagationInternational Journal of Computer Vision, 2014
- Submodular Function Maximization2014
- Unsupervised Joint Object Discovery and Segmentation in Internet Images2013
- Weakly Supervised Localization and Learning with Generic KnowledgeInternational Journal of Computer Vision, 2012
- Supervised Label Transfer for Semantic Segmentation of Street Scenes2010
- Improving Spatial Support for Objects via Multiple Segmentations2007
- "GrabCut"ACM Transactions on Graphics, 2004
- An experimental comparison of min-cut/max- flow algorithms for energy minimization in visionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Learning a classification model for segmentation2003