# Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average

Source: [Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average](<https://www.sota2.com/research/paper/68fa78971e209131cea792d8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:41:15.331Z

Authors: Wonjune Kim, Lae-kyoung Lee, Su-Yong An

Published: 2025-05-17T00:29:17.000Z

## Abstract

We report on the application of a high-capacity semantic segmentation pipeline to the GOOSE 2D Semantic Segmentation Challenge for unstructured off-road environments. Using a FlashInternImage-B backbone together with a UPerNet decoder, we adapt established techniques, rather than designing new ones, to the distinctive conditions of off-road scenes. Our training recipe couples strong photometric distortion augmentation (to emulate the wide lighting variations of outdoor terrain) with an Exponential Moving Average (EMA) of weights for better generalization. Using only the GOOSE training dataset, we achieve 88.8\\% mIoU on the validation set.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.11769>)

[PDF](<https://arxiv.org/pdf/2505.11769.pdf>)