- Instructor: WANG Lin ([email protected])
- TAS SU yin ([email protected]) and ZHU Qingyan ([email protected])
Office Hours: BY appointment only.
- Paper summary (10%)
- Paper presentation and discussion (30%)
- Group project and paper submission (50%)
- Attendance and Participation (10%)
| Dates | Topics | Active Learning |
|---|---|---|
| 2/8 | Course introduction | |
| 2/10 | Course introduction | Overview of computer vision |
| 2/15 | Deep learning basics | TAs’ lectures for CNN basics, algorithm basics and Pytorch tuorial |
| 2/17 | Deep learning basics | TAs’ lectures for CNN basics, algorithm basics and Pytorch tuorial |
| 2/22 | DNN models in computer vision (GAN, RNN, GNN) | |
| 2/24 | DNN models in computer vision (GAN, RNN, GNN) | (1) Persenation (2) Review due 2/27 (3) Project meetings |
| 3/1 | Learning methods in computer vision (Transfer learning, domain adaptation, self/semi-supervised learning) | |
| 3/3 | Learning methods in computer vision ((Transfer learning, domain adaptation, self/semi-supervised learning)) | (1) Persenation (2) Review due 3/6 |
| 3/8 | Deep learning for image restoration and enhancement (I) deblurring, deraining, dehazing | |
| 3/10 | Deep learning for image restoration and enhancement (I) deblurring, deraining, dehazing | (1) Persenation (2) Review due 3/13 (3) Project proposal kick-off (one page) |
| 3/15 | Deep learning for image restoration and enhancement (II) Super-resolution, HDR imaging | |
| 3/17 | Deep learning for image restoration and enhancement (II) Super-resolution, HDR imaging | (1) Persenation (2) Review due 3/20 |
| 3/22 | Deep learning for scene understanding (I) Object detection tracking | |
| 3/24 | Deep learning for scene understanding (I) Object detection tracking | Project mid-term presentation |
| 3/29 | Deep learning for scene understanding (II) Semantic segmentation | |
| 3/31 | Deep learning for scene understanding (II) Semantic segmentation | (1) Persenation (2) Review due 4/3 |
| 4/5 | Computer vision with novel cameras (I) Event camera-based vision | |
| 4/7 | Computer vision with novel cameras (I) Event camera-based vision | (1) Persenation (2) Review due 4/10 |
| 4/12 | Computer vision with novel cameras (II) Thermal/360 camera-based vision | |
| 4/14 | Computer vision with novel cameras (II) Thermal/360 camera-based vision | (1) Persenation (2) Review due 4/17 (3) Project meetings |
| 4/19 | Special vision problems (Learning in adverse visual conditions) | |
| 4/21 | Special vision problems (Learning in adverse visual conditions) | (1) Persenation (2) Review due 4/24 |
| 4/26 | Adversarial robustness in computer vision (Adversrial attack and defense) | |
| 4/28 | Adversarial robustness in computer vision (Adversrial attack and defense) | (1) Persenation (2) Review due 4/31 (3) Project meetings |
| 5/3 | Potential and Challenges in computer vision (data, computation, learning, sensor) (self-driving and robotics) | |
| 5/5 | Potential and Challenges in computer vision (data, computation, learning, sensor) (self-driving and robotics) | (1) TA/Student lectures (2) final project Q/A |
| 5/10 | Project presentation and final paper submission | |
| 5/12 | Project presentation and final paper submission | Submission due 5/26 |