Object recognition as ranking holistic figure-ground hypotheses
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1712-1719
- https://doi.org/10.1109/cvpr.2010.5539839
Abstract
We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up, object independent process. Decisions are performed based on continuous estimates of the spatial overlap between image segment hypotheses and each putative class. We differ from existing approaches not only in our seemingly unreasonable assumption that good object-level segments can be obtained in a feed-forward fashion, but also in framing recognition as a regression problem. Instead of focusing on a one-vs-all winning margin that can scramble ordering inside the non-maximum (non-winning) set, learning produces a globally consistent ranking with close ties to segment quality, hence to the extent entire object or part hypotheses spatially overlap with the ground truth. We demonstrate results beyond the current state of the art for image classification, object detection and semantic segmentation, in a number of challenging datasets including Caltech-101, ETHZ-Shape and PASCAL VOC 2009.Keywords
This publication has 16 references indexed in Scilit:
- Constrained parametric min-cuts for automatic object segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Associative hierarchical CRFs for object class image segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A discriminatively trained, multiscale, deformable part modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A Simple High Performance Approach to Semantic SegmentationPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- Representing shape with a spatial pyramid kernelPublished by Association for Computing Machinery (ACM) ,2007
- Accurate Object Detection with Deformable Shape Models Learnt from ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Support Kernel Machines for Object RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- OBJ CUTPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005