# How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments

arXiv: https://arxiv.org/abs/2605.29599 · HTML: https://mlsanity.com/paper/2605.29599/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 20 of 20)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [RELLIS-3D Dataset: Data, Benchmarks and Analysis](https://mlsanity.com/paper/2011.12954/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations](https://mlsanity.com/paper/1807.01697/) (2018)
- [Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2012.10782/) (2020)
- [GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments](https://mlsanity.com/paper/2103.04233/) (2021)
- [The GOOSE Dataset for Perception in Unstructured Environments](https://mlsanity.com/paper/2310.16788/) (2023)
- [Deep Texture Manifold for Ground Terrain Recognition](https://mlsanity.com/paper/1803.10896/) (2018)
- [Deep Gaussian Mixture Models](https://mlsanity.com/paper/1711.06929/) (2017)
- [OFFSEG: A Semantic Segmentation Framework For Off-Road Driving](https://mlsanity.com/paper/2103.12417/) (2021)
- [A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios](https://mlsanity.com/paper/2103.13109/) (2021)
- [Multi-feature Co-learning for Image Inpainting](https://mlsanity.com/paper/2205.10578/) (2022)
- [Uncertainty-aware Perception Models for Off-road Autonomous Unmanned Ground Vehicles](https://mlsanity.com/paper/2209.11115/) (2022)

## Built on by (most cited first, 1 of 1)

- [Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking](https://mlsanity.com/paper/2609.23673/) (2026)

## Abstract (arXiv)

Semantic segmentation is crucial for autonomous navigation in off-road environments, enabling precise classification of surroundings to identify traversable regions. However, distinctive factors inherent to off-road conditions, such as source-target domain discrepancies and sensor corruption from rough terrain, can result in distribution shifts that alter the data differently from the trained conditions. This often leads to inaccurate semantic label predictions and subsequent failures in navigation tasks. To address this, we propose ST-Seg, a novel framework that expands the source distribution through style expansion (SE) and texture regularization (TR). Unlike prior methods that implicitly apply generalization within a fixed source distribution, ST-Seg offers an intuitive approach for distribution shift. Specifically, SE broadens domain coverage by generating diverse realistic styles, augmenting the limited style information of the source domain. TR stabilizes local texture representation affected by style-augmented learning through a deep texture manifold. Experiments across various distribution-shifted target domains demonstrate the effectiveness of ST-Seg, with substantial improvements over existing methods. These results highlight the robustness of ST-Seg, enhancing the real-world applicability of semantic segmentation for off-road navigation.