Saved in:
Bibliographic Details
Main Authors: Hsu, Chih-Chung, Wu, I-Hsuan, Tseng, Wen-Hai, Cheng, Ching-Heng, Wu, Ming-Hsuan, Jiang, Jin-Hui, Hsiao, Yu-Jou
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.06991
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912370159255552
author Hsu, Chih-Chung
Wu, I-Hsuan
Tseng, Wen-Hai
Cheng, Ching-Heng
Wu, Ming-Hsuan
Jiang, Jin-Hui
Hsiao, Yu-Jou
author_facet Hsu, Chih-Chung
Wu, I-Hsuan
Tseng, Wen-Hai
Cheng, Ching-Heng
Wu, Ming-Hsuan
Jiang, Jin-Hui
Hsiao, Yu-Jou
contents This report presents our semantic segmentation framework developed by team ACVLAB for the ICRA 2025 GOOSE 2D Semantic Segmentation Challenge, which focuses on parsing outdoor scenes into nine semantic categories under real-world conditions. Our method integrates a Swin Transformer backbone enhanced with Rotary Position Embedding (RoPE) for improved spatial generalization, alongside a Color Shift Estimation-and-Correction module designed to compensate for illumination inconsistencies in natural environments. To further improve training stability, we adopt a quantile-based denoising strategy that downweights the top 2.5\% of highest-error pixels, treating them as noise and suppressing their influence during optimization. Evaluated on the official GOOSE test set, our approach achieved a mean Intersection over Union (mIoU) of 0.848, demonstrating the effectiveness of combining color correction, positional encoding, and error-aware denoising in robust semantic segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06991
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding
Hsu, Chih-Chung
Wu, I-Hsuan
Tseng, Wen-Hai
Cheng, Ching-Heng
Wu, Ming-Hsuan
Jiang, Jin-Hui
Hsiao, Yu-Jou
Computer Vision and Pattern Recognition
This report presents our semantic segmentation framework developed by team ACVLAB for the ICRA 2025 GOOSE 2D Semantic Segmentation Challenge, which focuses on parsing outdoor scenes into nine semantic categories under real-world conditions. Our method integrates a Swin Transformer backbone enhanced with Rotary Position Embedding (RoPE) for improved spatial generalization, alongside a Color Shift Estimation-and-Correction module designed to compensate for illumination inconsistencies in natural environments. To further improve training stability, we adopt a quantile-based denoising strategy that downweights the top 2.5\% of highest-error pixels, treating them as noise and suppressing their influence during optimization. Evaluated on the official GOOSE test set, our approach achieved a mean Intersection over Union (mIoU) of 0.848, demonstrating the effectiveness of combining color correction, positional encoding, and error-aware denoising in robust semantic segmentation.
title Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.06991