CVJun 9, 2024

Technical Report for CVPR 2024 WeatherProof Dataset Challenge: Semantic Segmentation on Paired Real Data

arXiv:2407.01579v1
Originality Synthesis-oriented
AI Analysis

This work addresses semantic segmentation for weather-affected images, which is an incremental improvement using existing methods on new data.

The authors tackled semantic segmentation on weather-degraded images by using a pre-trained InternImage foundation model trained with varying noise levels, achieving second place in the CVPR 2024 WeatherProof Dataset Challenge with 45.1 mIOU.

This technical report presents the implementation details of 2nd winning for CVPR'24 UG2 WeatherProof Dataset Challenge. This challenge aims at semantic segmentation of images degraded by various degrees of weather from all around the world. We addressed this problem by introducing a pre-trained large-scale vision foundation model: InternImage, and trained it using images with different levels of noise. Besides, we did not use additional datasets in the training procedure and utilized dense-CRF as post-processing in the final testing procedure. As a result, we achieved 2nd place in the challenge with 45.1 mIOU and fewer submissions than the other winners.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes