2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | MLR-APPL-IP-1.5 | ||
| Paper Title | Learning to Disentangle Representations for Rain Streak Removal | ||
| Authors | Younkwan Lee, Hyeongjun Yoo, Moongu Jeon, Gwangju Institute of Science and Technology, Republic of Korea | ||
| Session | MLR-APPL-IP-1: Machine learning for image processing 1 | ||
| Location | Area E | ||
| Session Time: | Monday, 20 September, 13:30 - 15:00 | ||
| Presentation Time: | Monday, 20 September, 13:30 - 15:00 | ||
| Presentation | Poster | ||
| Topic | Applications of Machine Learning: Machine learning for image processing | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Rain streak removal is an important task in many real-world vision applications since rain streaks in the air largely threaten the performance of visual analytics. When training conventional models, it is common to remove rain streaks without defining explicitly biased information. Although it is often regarded that learned representation is effective in capturing informativeness, it is still likely to indicate incongruent information to spoil removal while learning biased representation. To handle this issue, we employ an information-theoretic concept to define disentangled representation which is divided into shared and biased characteristics respectively. Our key idea is to remove biased feature representations from a set of co-occurrence features while preserving details using mutual information. We achieve this by proposing a novel stage-wise training strategy that captures a more discriminative and pure factor that preserves details. Specifically, we utilize an adversarial objective that explicitly defines each representation to enforce disentanglement. Extensive computational experiments on five benchmark datasets show the superiority of our new model against state-of-the-art methods. | ||