Kernelized structural SVM learning for supervised object segmentation
- 1 June 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2153-2160
- https://doi.org/10.1109/cvpr.2011.5995597
Abstract
Object segmentation needs to be driven by top-down knowledge to produce semantically meaningful results. In this paper, we propose a supervised segmentation approach that tightly integrates object-level top down information with low-level image cues. The information from the two levels is fused under a kernelized structural SVM learning framework. We defined a novel nonlinear kernel for comparing two image-segmentation masks. This kernel combines four different kernels: the object similarity kernel, the object shape kernel, the per-image color distribution kernel, and the global color distribution kernel. Our experiments show that the structured SVM algorithm finds bad segmentations of the training examples given the current scoring function and punishes these bad segmentations to lower scores than the example (good) segmentations. The result is a segmentation algorithm that not only knows what good segmentations are, but also learns potential segmentation mistakes and tries to avoid them. Our proposed approach can obtain comparable performance to other state-of-the-art top-down driven segmentation approaches yet is flexible enough to be applied to widely different domains.Keywords
This publication has 18 references indexed in Scilit:
- Layered object detection for multi-class segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Delving deeper into the whorl of flower segmentationImage and Vision Computing, 2009
- Learning to Combine Bottom-Up and Top-Down SegmentationInternational Journal of Computer Vision, 2008
- Support Vector Training of Protein Alignment ModelsPublished by Springer Science and Business Media LLC ,2007
- Learning The Discriminative Power-Invariance Trade-OffPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- OBJ CUTPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Image Parsing: Unifying Segmentation, Detection, and RecognitionInternational Journal of Computer Vision, 2005
- "GrabCut"Published by Association for Computing Machinery (ACM) ,2004
- What energy functions can be minimized via graph cuts?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Multiple kernel learning, conic duality, and the SMO algorithmPublished by Association for Computing Machinery (ACM) ,2004