Feature division and fusion for multi-task dense prediction

• Main Author: Gao, Yuhan
• Other Authors: Jiang Xudong
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2025
• Subjects: Engineering; Multi-task learning; Cross attention; Dense prediction; Task-specificity
• Online Access: https://hdl.handle.net/10356/184728

In MTL, how to simplify the high-level task network structure while improving the model’s performance across multiple tasks, while effectively utilizing the inter-task correlation to further enhance the model’s generalization ability, re mains a challenging problem. Most multi-task dense predic...