Yunfei Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yunfei Xie has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Alan Yuille
Johns Hopkins University
2 shared publications - Cihang Xie
UC Santa Cruz
2 shared publications - Jieru Mei
Johns Hopkins University
2 shared publications Haoyu Zhang
City University of Hong Kong
1 shared publicationJuncheng Wu
University of California
1 shared publication- Shoudong Han
Huazhong University of Science and Technology
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14470-14481
SCING: Toward More Efficient and Robust Person Re-Identification Through Selective Cross-Modal Prompt Tuning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14470-14481
SCING: Toward More Efficient and Robust Person Re-Identification Through Selective Cross-Modal Prompt Tuning
- 29 November 2024
- Published by Springer Nature
- p. 341-356
From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
- 29 November 2024
- Published by Springer Nature
- p. 341-356
From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
- Open Access
From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
In this paper, we introduce a hierarchical transformer-based model designed for sophisticated image segmentation tasks, effectively bridging the granularity of part segmentation with the comprehensive scope of object segmentation. At the heart of our approach is a multi-level representation strategy, which systematically advances from individual pixels to superpixels, and ultimately to cohesive group formations. This architecture is underpinned by two pivotal aggregation strategies: local aggregation and global aggregation. Local aggregation is employed to form superpixels, leveraging the inherent redundancy of the image data to produce segments closely aligned with specific parts of the object, guided by object-level supervision. In contrast, global aggregation interlinks these superpixels, organizing them into larger groups that correlate with entire objects and benefit from part-level supervision. This dual aggregation framework ensures a versatile adaptation to varying supervision inputs while maintaining computational efficiency. Our methodology notably improves the balance between adaptability across different supervision modalities and computational manageability, culminating in significant enhancement in segmentation performance. When tested on the PartImageNet dataset, our model achieves a substantial increase, outperforming the previous state-of-the-art by 2.8% and 0.8% in mIoU scores for part and object segmentation, respectively. Similarly, on the Pascal Part dataset, it records performance enhancements of 1.5% and 2.0% for part and object segmentation, respectively.
Open AccessFrom Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
In this paper, we introduce a hierarchical transformer-based model designed for sophisticated image segmentation tasks, effectively bridging the granularity of part segmentation with the comprehensive scope of object segmentation. At the heart of our approach is a multi-level representation strategy, which systematically advances from individual pixels to superpixels, and ultimately to cohesive group formations. This architecture is underpinned by two pivotal aggregation strategies: local aggregation and global aggregation. Local aggregation is employed to form superpixels, leveraging the inherent redundancy of the image data to produce segments closely aligned with specific parts of the object, guided by object-level supervision. In contrast, global aggregation interlinks these superpixels, organizing them into larger groups that correlate with entire objects and benefit from part-level supervision. This dual aggregation framework ensures a versatile adaptation to varying supervision inputs while maintaining computational efficiency. Our methodology notably improves the balance between adaptability across different supervision modalities and computational manageability, culminating in significant enhancement in segmentation performance. When tested on the PartImageNet dataset, our model achieves a substantial increase, outperforming the previous state-of-the-art by 2.8% and 0.8% in mIoU scores for part and object segmentation, respectively. Similarly, on the Pascal Part dataset, it records performance enhancements of 1.5% and 2.0% for part and object segmentation, respectively.