mlsanityData to 14 Oct 2026

COARSE: Collaborative Pseudo-Labeling with Coarse Real Labels for Off-Road Semantic Segmentation

arXiv 2503.03947 ↗First posted 5 Mar 2025cs.CV cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous off-road navigation faces challenges due to diverse, unstructured environments, requiring robust perception with both geometric and semantic understanding. However, scarce densely labeled semantic data limits generalization across domains. Simulated data helps, but introduces domain adaptation issues. We propose COARSE, a semi-supervised domain adaptation framework for off-road semantic segmentation, leveraging sparse, coarse in-domain labels and densely labeled out-of-domain data. Using pretrained vision transformers, we bridge domain gaps with complementary pixel-level and patch-level decoders, enhanced by a collaborative pseudo-labeling strategy on unlabeled data. Evaluations on RUGD and Rellis-3D datasets show significant improvements of 9.7% and 8.4% respectively, versus only using coarse data. Tests on real-world off-road vehicle data in a multi-biome setting further demonstrate COARSE's applicability.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 5 Mar 2025.

Builds on

28 of 37 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  10. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  11. 2021Vision Transformers for Dense Predictioncited by 1,803
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
16 more
  1. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  2. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  3. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  4. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  5. 2021Intriguing Properties of Vision Transformerscited by 446
  6. 2019Confidence Regularized Self-Trainingcited by 419
  7. 2021Understanding Robustness of Transformers for Image Classificationcited by 249
  8. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  9. 2021Vision Transformers are Robust Learnerscited by 207
  10. 2022Understanding The Robustness in Vision Transformerscited by 144
  11. 2020RELLIS-3D Dataset: Data, Benchmarks and Analysiscited by 119
  12. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 100
  13. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  14. 2022Urban Scene Semantic Segmentation with Low-Cost Coarse Annotationcited by 11
  15. 2024Vision-Based Detection of Uncooperative Targets and Components on Small Satellitescited by 3
  16. 2024Few-shot Semantic Learning for Robust Multi-Biome 3D Semantic Mapping in Off-Road Environmentscited by 3

Built on by

Not cited yet.