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.
Excavating in the wild: The goose-ex dataset for semantic segmentation,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
An adapted Mask2Former with 200 queries, a Feature Refinement Module, and auxiliary rare-class supervision reaches 70.08% mIoU on the GOOSE 2D FGSS benchmark.
A competition entry won first place on the GOOSE 2D challenge leaderboard by pairing a DINOv3 ViT-L/16 backbone with ViT-Adapter and Mask2Former plus multi-scale TTA and checkpoint ensemble, reaching 76.57% composite score.
citing papers explorer
-
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.
-
GOOSE-M2F: Adapting Mask2Former for High-Fidelity, Long-Tailed Fine-Grained Semantic Segmentation in Unstructured Outdoor Terrain
An adapted Mask2Former with 200 queries, a Feature Refinement Module, and auxiliary rare-class supervision reaches 70.08% mIoU on the GOOSE 2D FGSS benchmark.
-
Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Leveraging DINOv3 for Robust Outdoor Scene Understanding in Field Robotics
A competition entry won first place on the GOOSE 2D challenge leaderboard by pairing a DINOv3 ViT-L/16 backbone with ViT-Adapter and Mask2Former plus multi-scale TTA and checkpoint ensemble, reaching 76.57% composite score.