Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation
Suyog Dutt Jain Kristen Grauman
University of Texas at Austin
[pdf] [supplementary] [bibtex][poster][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
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|
|Goal: Given a batch of ``n" images with a fixed time budget ``B", we find the optimal
annotation tool for each image
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.
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][data]