Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 360-367
- https://doi.org/10.1109/cvpr.2014.53
Abstract
We present an approach MSIL-CRF that incorporates multiple instance learning (MIL) into conditional random fields (CRFs). It can generalize CRFs to work on training data with uncertain labels by the principle of MIL. In this work, it is applied to saving manual efforts on annotating training data for semantic segmentation. Specifically, we consider the setting in which the training dataset for semantic segmentation is a mixture of a few object segments and an abundant set of objects' bounding boxes. Our goal is to infer the unknown object segments enclosed by the bounding boxes so that they can serve as training data for semantic segmentation. To this end, we generate multiple segment hypotheses for each bounding box with the assumption that at least one hypothesis is close to the ground truth. By treating a bounding box as a bag with its segment hypotheses as structured instances, MSIL-CRF selects the most likely segment hypotheses by leveraging the knowledge derived from both the labeled and uncertain training data. The experimental results on the Pascal VOC segmentation task demonstrate that MSIL-CRF can provide effective alternatives to manually labeled segments for semantic segmentation.Keywords
This publication has 19 references indexed in Scilit:
- Weakly-Supervised Dual Clustering for Image Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Hough Forest Random Field for Object Recognition and SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Discriminative clustering for image co-segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Class segmentation and object localization with superpixel neighborhoodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Image segmentation with a bounding box priorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and ContextInternational Journal of Computer Vision, 2007
- Hidden Conditional Random FieldsIeee Transactions On Pattern Analysis and Machine Intelligence, 2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- "GrabCut"Published by Association for Computing Machinery (ACM) ,2004
- On the limited memory BFGS method for large scale optimizationMathematical Programming, 1989