Yiding Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yiding Liu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Houqiang Li
Department of Electronic Engineering and Information Science University of Science and Technology of China
2 shared publicationsWengang Zhou
Department of Electronic Engineering and Information Science University of Science and Technology of China
2 shared publicationsBin Li
Microsoft Research
1 shared publication- Bin Li
Microsoft Research Asia, Beijing, China
1 shared publication Jizheng Xu
Microsoft Research
1 shared publication- Jizheng Xu
Microsoft Research Asia, Beijing, China
1 shared publication
Latest Publications
- Open Access
Affinity Derivation and Graph Merge for Instance Segmentation
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine-grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.
Open AccessAffinity Derivation and Graph Merge for Instance Segmentation
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine-grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.
- 7 October 2018
- Published by Springer Nature
- p. 708-724
Affinity Derivation and Graph Merge for Instance Segmentation
- 7 October 2018
- Published by Springer Nature
- p. 708-724
Affinity Derivation and Graph Merge for Instance Segmentation