Weifeng Ge
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Weifeng Ge has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Dongyang Zhao
School of Computer Science, Fudan University,Shanghai,China
1 shared publication - Hongyu Ma
Guangdong Provincial Key Laboratory of Marine Biotechnology, Shantou University, Shantou 515063, China
1 shared publication - Lei Wu
Nanjing Agricultural University
1 shared publication - Lingming Kong
Psychiatric Research Center, No. 904th Hospital of Joint Logistic Support Force, Changzhou, Jiangsu, China.
1 shared publication - Peng Jiang
CIMMYT-JAAS Joint Center for Wheat Diseases, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China
1 shared publication - Tao Gui
Fudan University, China
1 shared publication
Latest Publications
- 19 March 2025
- Published by Springer Nature in Computational Statistics
- Vol. 40 (8) , 4187-4207
An improved preconditioned unsupervised K-means clustering algorithm
- 19 March 2025
- Published by Springer Nature in Computational Statistics
- Vol. 40 (8) , 4187-4207
An improved preconditioned unsupervised K-means clustering algorithm
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 30, 17787-17796
Correspondence Transformers with Asymmetric Feature Learning and Matching Flow Super-Resolution
This paper solves the problem of learning dense visual correspondences between different object instances of the same category with only sparse annotations. We decompose this pixel-level semantic matching problem into two easier ones: (i) First, local feature descriptors of source and target images need to be mapped into shared semantic spaces to get coarse matching flows. (ii) Second, matching flows in low resolution should be refined to generate accurate point-to-point matching results. We propose asymmetric feature learning and matching flow super-resolution based on vision transformers to solve the above problems. The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts. Then matching flow in low resolutions is enhanced by a super-resolution network to get accurate correspondences. Our pipeline is built upon vision transformers and can be trained in an end-to-end manner. Extensive experimental results on several popular benchmarks, such as PF-PASCAL, PF-WILLOW, and SPair-71 K, demonstrate that the proposed method can catch subtle semantic differences in pixels efficiently. Code is available on https://github.com/YXSUNMADMAX/ACTR.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 30, 17787-17796
Correspondence Transformers with Asymmetric Feature Learning and Matching Flow Super-Resolution
This paper solves the problem of learning dense visual correspondences between different object instances of the same category with only sparse annotations. We decompose this pixel-level semantic matching problem into two easier ones: (i) First, local feature descriptors of source and target images need to be mapped into shared semantic spaces to get coarse matching flows. (ii) Second, matching flows in low resolution should be refined to generate accurate point-to-point matching results. We propose asymmetric feature learning and matching flow super-resolution based on vision transformers to solve the above problems. The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts. Then matching flow in low resolutions is enhanced by a super-resolution network to get accurate correspondences. Our pipeline is built upon vision transformers and can be trained in an end-to-end manner. Extensive experimental results on several popular benchmarks, such as PF-PASCAL, PF-WILLOW, and SPair-71 K, demonstrate that the proposed method can catch subtle semantic differences in pixels efficiently. Code is available on https://github.com/YXSUNMADMAX/ACTR.