| Paper ID | IVMSP-29.5 |
| Paper Title |
NLKD: using coarse annotations for semantic segmentation based on knowledge distillation |
| Authors |
Dong Liang, Yun Du, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China; Han Sun, Liyan Zhang, Ningzhong Liu, Mingqiang Wei, Nanjing University of Aeronautics and Astronautics, China |
| Session | IVMSP-29: Semantic Segmentation |
| Location | Gather.Town |
| Session Time: | Friday, 11 June, 13:00 - 13:45 |
| Presentation Time: | Friday, 11 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Image, Video, and Multidimensional Signal Processing: [IVARS] Image & Video Analysis, Synthesis, and Retrieval |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Modern supervised learning relies on a large amount of training data, yet there are many noisy annotations in real datasets. For semantic segmentation tasks, pixel-level annotation noise is typically located at the edge of an object, while pixels within objects are fine-annotated. We argue the coarse annotations can provide instructive supervised information to guide model training rather than be discarded. This paper proposes a noise learning framework based on knowledge distillation NLKD, to improve segmentation performance on unclean data. It utilizes a teacher network to guide the student network that constitutes the knowledge distillation process. The teacher and student generate the pseudo-labels and jointly evaluate the quality of annotations to generate weights for each sample. Experiments demonstrate the effectiveness of NLKD, and we observe better performance with boundary-aware teacher networks and evaluation metrics. Furthermore, the proposed approach is model-independent and easy to implement, appropriate for integration with other tasks and models. |
