Boundary perception guidance: A scribble-supervised semantic segmentation approach
- Publication Type:
- Conference Proceeding
- IJCAI International Joint Conference on Artificial Intelligence, 2019, 2019-August, pp. 3663-3669
- Issue Date:
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
© 2019 International Joint Conferences on Artificial Intelligence. All rights reserved. Semantic segmentation suffers from the fact that densely annotated masks are expensive to obtain. To tackle this problem, we aim at learning to segment by only leveraging scribbles that are much easier to collect for supervision. To fully explore the limited pixel-level annotations from scribbles, we present a novel Boundary Perception Guidance (BPG) approach, which consists of two basic components, i.e. prediction refinement and boundary regression. Specifically, the prediction refinement progressively makes a better segmentation by adopting an iterative upsampling and a semantic feature enhancement strategy. In the boundary regression, we employ class-agnostic edge maps for supervision to effectively guide the segmentation network in localizing the boundaries between different semantic regions, leading to producing fine-grained representation of feature maps for semantic segmentation. Experimental results on the PASCAL VOC 2012 demonstrate the proposed BPG achieves mIoU of 73.2% without fully connected Conditional Random Field (CRF) and 76.0% with CRF, setting up the new state-of-the-art in literature.
Please use this identifier to cite or link to this item: