This course examines the transformative impact of deep learning in computer vision. Students will establish a solid foundation while engaging with state-of-the-art techniques, ranging from convolutional neural networks (CNNs), Transformers, diffusion models, and 3D vision to multimodal large language models (MLLMs). The course emphasizes the design of model architectures, training methodologies, and real-world applications. Through hands-on projects and critical theoretical discussions, students will develop comprehensive expertise in designing, training, and optimizing deep learning models for complex visual tasks. Ultimately, the course prepares students for advanced research and professional careers in the rapidly evolving field of computer vision. 

1. 本校建議 A+ 比例上限為 20% ，非強制規定，授課教師可依課程要求調整，建議必修課程參考。
2. 本校採用等第制評定成績，學生成績評量辦法中的百分制分數區間與單科成績對照表僅供參考，授課教師可依等第定義調整分數區間。詳見學習評量專區 (連結)。