Author:
Lin Zheng,Zhang Zhao,Zhu Zi-Yue,Fan Deng-Ping,Liu Xia-Lei
Abstract
AbstractInteractive image segmentation (IIS) is an important technique for obtaining pixel-level annotations. In many cases, target objects share similar semantics. However, IIS methods neglect this connection and in particular the cues provided by representations of previously segmented objects, previous user interaction, and previous prediction masks, which can all provide suitable priors for the current annotation. In this paper, we formulate a sequential interactive image segmentation (SIIS) task for minimizing user interaction when segmenting sequences of related images, and we provide a practical approach to this task using two pertinent designs. The first is a novel interaction mode. When annotating a new sample, our method can automatically propose an initial click proposal based on previous annotation. This dramatically helps to reduce the interaction burden on the user. The second is an online optimization strategy, with the goal of providing semantic information when annotating specific targets, optimizing the model with dense supervision from previously labeled samples. Experiments demonstrate the effectiveness of regarding SIIS as a particular task, and our methods for addressing it.
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Graphics and Computer-Aided Design,Computer Vision and Pattern Recognition
Reference54 articles.
1. Maninis, K. K.; Caelles, S.; Pont-Tuset, J.; Van Gool, L. Deep extreme cut: From extreme points to object segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 616–625, 2018.
2. Lecture Notes in Computer Science;H Le,2018
3. Jain, S. D.; Grauman, K. Click carving: Interactive object segmentation in images and videos with point clicks. International Journal of Computer Vision Vol. 127, No. 9, 1321–1344, 2019.
4. Xu, N.; Price, B.; Cohen, S.; Yang, J. M.; Huang, T. Deep GrabCut for object selection. In: Proceedings of the British Machine Vision Conference, 182.1–182.12, 2017.
5. Majumder, S.; Rai, A.; Khurana, A.; Yao, A. Two-in-one refinement for interactive segmentation. In: Proceedings of the 31st British Machine Vision Conference, 2020.