Kernelized Structural SVM Learning for Supervised Object Segmentation
Venue
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 2011
Publication Year
2011
Authors
Luca Bertelli, Tianli Yu, Diem Vu, Burak Gokturk
BibTeX
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.
