A BENCHMARK FOR SEMANTIC IMAGE SEGMENTATION

1Hui Li   1Jianfei Cai   2Thi Nhat Anh Nguyen   1Jianmin Zheng  

1 Nanyang Technological University, Singapore     2Danang University of Technology, Vietnam    



Fig.1 Examples of semantic image segmentation.
Each nature image is followed by a few semantic segmentations at different levels. In general, each image is segmented into a small set of meaningful segments with considerable sizes.

Abstract

Though quite a few image segmentation benchmark datasets have been constructed, there is no suitable benchmark for semantic image segmentation. In this paper, we construct a benchmark for such a purpose, where the ground-truths are generated by leveraging the existing fine granular groundtruths in Berkeley Segmentation Dataset (BSD) as well as using an interactive segmentation tool for new images. We also propose a percept-tree-based region merging strategy for dynamically adapting the ground-truth for evaluating test segmentation. Moreover, we propose a new evaluation metric that is easy to understand and compute, and does not require boundary matching. Experimental results show that, compared with BSD, the generated ground-truth dataset is more suitable for evaluating semantic image segmentation, and the conducted user study demonstrates that the proposed evaluation metric matches user ranking very well.



Citation - BibTeX

Hui Li, Jianfei Cai, Thi Nhat Anh Nguyen, Jianmin Zheng. A BENCHMARK FOR SEMANTIC IMAGE SEGMENTATION. IEEE ICME 2013. [ Pdf ] [ Poster ] [ BibTeX ]

Download

You can download the [ DataSet ] (6.81MB) and the [ Evaluation Software ] (5.12MB).