Can I read D2SL: Decouple Defogging and Semantic Learning for Foggy Domain-Adaptive Segmentation on EtoBox?

D2SL: Decouple Defogging and Semantic Learning for Foggy Domain-Adaptive Segmentation by Sun, Xuan; An, Zhanfu; Liu, Yuyu is a scholarly article available to read on EtoBox.

What is D2SL: Decouple Defogging and Semantic Learning for Foggy Domain-Adaptive Segmentation about?

We investigated domain adaptive semantic segmentation in foggy weather scenarios, which aims to enhance the utilization of unlabeled foggy data and improve the model's adaptability to foggy conditions. Current methods rely on clear images as references, jointly learning defogging and segmentation for foggy images. Despite making some progress, there are still two main drawbacks: (1) the coupling of segmentation and defogging feature representations, resulting in a decrease in semantic representation capability, and (2) the failure to leverage real fog priors in unlabeled foggy data, leading to insufficient model generalization ability. To address these issues, we propose a novel training framework, Decouple Defogging and Semantic learning, called D2SL, aiming to alleviate the adverse impact of defogging tasks on the final segmentation task. In this framework, we introduce a domain-consistent transfer strategy to establish a connection between defogging and segmentation tasks. Furthermore, we design a real fog transfer strategy to improve defogging effects by fully leveraging the fog priors from real foggy images. Our approach enhances the semantic representations required for segme

Author

Sun, Xuan; An, Zhanfu; Liu, Yuyu

Published

2024

Language

EN