REVIEW 1 cited by
Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 1 Pith paper
-
SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation
Reports a 4th-place GOOSE 2D challenge entry adapting SAM3 with self-distillation on select classes and image-level multi-scale TTA, reaching 69.73% mIoU, with photometric distortion as the largest gain source.
Discussion (0). Sign in to comment.