Title | ||
---|---|---|
Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic Segmentation |
Abstract | ||
---|---|---|
How to import image-level labels as weak supervision to direct the region-level labeling task is the core task of weakly-supervised semantic segmentation. In this paper, we focus on designing an effective but simple weakly-supervised constraint, and propose an exclusive constrained discriminative learning model for image semantic segmentation. To be specific, we employ a discriminative linear regression model to assign subsets of superpixels with different labels. During the assignment, we construct an exclusive weakly-supervised constraint term to suppress the labeling responses of each superpixel on the labels outside its parent image-level label set. Besides, a spectral smoothing term is integrated to encourage that both visually and semantically similar superpixels have similar labels. Combining these terms, we formulate the problem as a convex objective function, which can be easily optimized via alternative iterations. Extensive experiments on MSRC-21 and LabelMe datasets demonstrate the effectiveness of the proposed model. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1145/2733373.2806329 | ACM Multimedia |
Keywords | Field | DocType |
Semantic Segmentation,Weak Supervision | LabelMe,Pattern recognition,Computer science,Segmentation,Regular polygon,Smoothing,Artificial intelligence,Discriminative model,Machine learning,Discriminative learning,Linear regression | Conference |
Citations | PageRank | References |
1 | 0.35 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peng Ying | 1 | 1 | 0.35 |
Jing Liu | 2 | 1781 | 88.09 |
Hanqing Lu | 3 | 4620 | 291.38 |
Songde Ma | 4 | 1 | 0.35 |