Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Object Recognition by Integrating Multiple Image Segmentations
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
International Journal of Computer Vision
Robust Higher Order Potentials for Enforcing Label Consistency
International Journal of Computer Vision
Improving the fisher kernel for large-scale image classification
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Graph cut based inference with co-occurrence statistics
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Contour Detection and Hierarchical Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Efficient Approach to Semantic Segmentation
International Journal of Computer Vision
Efficient region search for object detection
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Are spatial and global constraints really necessary for segmentation?
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Markov random fields for sketch based video retrieval
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
| Hi-index | 0.00 |
There is a general trend in recent methods to use image regions (i.e. super-pixels) obtained in an unsupervised way to enhance the semantic image segmentation task. This paper proposes a detailed study on the role and the benefit of using these regions, at different steps of the segmentation process. For the purpose of this benchmark, we propose a simple system for semantic segmentation that uses a hierarchy of regions. A patch based system with similar settings is compared, which allows us to evaluate the contribution of each component of the system. Both systems are evaluated on the standard MSRC-21 dataset and obtain competitive results. We show that the proposed region based system can achieve good results without any complex regularization, while its patch based counterpart becomes competitive when using image prior and regularization methods. The latter benefit more from a CRF based regularization, yielding to state-of-the-art results with simple constraints based only on the leaf regions exploited in the pairwise potential.