Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation
Suyog Dutt Jain Kristen Grauman
University of Texas at Austin
suyog@cs.utexas.edu
[pdf] [supplementary] [bibtex][poster][code] [data]
Predict the annotation modality that is sufficiently strong for accurate segmentation of a given image |
Learning to predict segmentation difficulty per modality (Training) |
Given a set of images with the foreground masks, we first simulate the user input. |
Use the overlap score between the resulting segmentation and ground truth to mark
an image
as ``easy" or ``hard" and train a linear SVM classifier (for each modality). |
Bounding box example of ``easy" vs ``hard" |
Learning to predict segmentation difficulty per modality (Testing) |
Use saliency detector to get a coarse estimate of foreground at test time. |
Liu et al. 2009 |
Compute the proposed features and use trained classifiers to predict difficulty |
Budgeted Selection |
Goal: Given a batch of ``n" images with a fixed time budget ``B", we find the optimal
annotation tool for each image |
Baselines:
Predicting segmentation difficulty per modality:
Difficulty prediction accuracy for each dataset (first three columns) and cross-dataset experiments (last column) |
Cascade selection - application to recognition
Task: Given a set of images with a common object, train a classifier to separate object
vs. non object regions.
How to get data labeled?
Budgeted selection - MTurk User study
Acknowledgements: This research is supported in part by ONR YIP N00014-12-1-0754.
Publication:
Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation. S. Jain and K. Grauman. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013. [pdf] [supplementary] [bibtex][poster] [code] [data]