A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+
This work addresses the problem of degraded image quality for semantic segmentation in adverse weather conditions, but it is incremental as it builds on existing methods for a specific challenge.
The paper tackled semantic segmentation in adverse weather by proposing a two-stage framework that uses video deraining to create pseudo ground truths and trains an InternImage network, achieving a competitive mIoU score of 0.43 and ranking 4th in the challenge.
This technical report presents our team's solution for the WeatherProof Dataset Challenge: Semantic Segmentation in Adverse Weather at CVPR'24 UG2+. We propose a two-stage deep learning framework for this task. In the first stage, we preprocess the provided dataset by concatenating images into video sequences. Subsequently, we leverage a low-rank video deraining method to generate high-fidelity pseudo ground truths. These pseudo ground truths offer superior alignment compared to the original ground truths, facilitating model convergence during training. In the second stage, we employ the InternImage network to train for the semantic segmentation task using the generated pseudo ground truths. Notably, our meticulously designed framework demonstrates robustness to degraded data captured under adverse weather conditions. In the challenge, our solution achieved a competitive score of 0.43 on the Mean Intersection over Union (mIoU) metric, securing a respectable rank of 4th.