3 papers
cs.CV2025
Learning an Ensemble Token from Task-driven Priors in Facial Analysis
Sunyong Seo, Semin Kim, Jongha Lee
Facial analysis exhibits task-specific feature variations. While Convolutional Neural Networks (CNNs) have enabled the fine-grained representation of spatial information, Vision Tr…
eess.IV2025
Full-scale Representation Guided Network for Retinal Vessel Segmentation
Sunyong Seo, Sangwook Yoo, Huisu Yoon
The U-Net architecture and its variants have remained state-of-the-art (SOTA) for retinal vessel segmentation over the past decade. In this study, we introduce a Full-Scale Guided…
cs.CV2025
Data Augmentation For Small Object using Fast AutoAugment
DaeEun Yoon, Semin Kim, SangWook Yoo +1
In recent years, there has been tremendous progress in object detection performance. However, despite these advances, the detection performance for small objects is significantly i…