# Mars Terrain Segmentation with Less Labels

arXiv: https://arxiv.org/abs/2202.00791 · HTML: https://mlsanity.com/paper/2202.00791/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [BADGR: An Autonomous Self-Supervised Learning-Based Navigation System](https://mlsanity.com/paper/2002.05700/) (2020)
- [Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning](https://mlsanity.com/paper/1912.03227/) (2019)
- [DeepTerramechanics: Terrain Classification and Slip Estimation for Ground Robots via Deep Learning](https://mlsanity.com/paper/1806.07379/) (2018)

## Built on by (most cited first, 7 of 7)

- [RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving](https://mlsanity.com/paper/2402.19341/) (2024)
- [Deep learning universal crater detection using Segment Anything Model (SAM)](https://mlsanity.com/paper/2304.07764/) (2023)
- [S5Mars: Semi-Supervised Learning for Mars Semantic Segmentation](https://mlsanity.com/paper/2207.01200/) (2022)
- [Improving Contrastive Learning on Visually Homogeneous Mars Rover Images](https://mlsanity.com/paper/2210.09234/) (2022)
- [Mixed-domain Training Improves Multi-Mission Terrain Segmentation](https://mlsanity.com/paper/2209.13674/) (2022)
- [Boulders Identification on Small Bodies Under Varying Illumination Conditions](https://mlsanity.com/paper/2210.16283/) (2022)
- [Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdoor Environments by Leveraging Synthetic Data](https://mlsanity.com/paper/2605.27644/) (2026)

## Abstract (arXiv)

Planetary rover systems need to perform terrain segmentation to identify drivable areas as well as identify specific types of soil for sample collection. The latest Martian terrain segmentation methods rely on supervised learning which is very data hungry and difficult to train where only a small number of labeled samples are available. Moreover, the semantic classes are defined differently for different applications (e.g., rover traversal vs. geological) and as a result the network has to be trained from scratch each time, which is an inefficient use of resources. This research proposes a semi-supervised learning framework for Mars terrain segmentation where a deep segmentation network trained in an unsupervised manner on unlabeled images is transferred to the task of terrain segmentation trained on few labeled images. The network incorporates a backbone module which is trained using a contrastive loss function and an output atrous convolution module which is trained using a pixel-wise cross-entropy loss function. Evaluation results using the metric of segmentation accuracy show that the proposed method with contrastive pretraining outperforms plain supervised learning by 2%-10%. Moreover, the proposed model is able to achieve a segmentation accuracy of 91.1% using only 161 training images (1% of the original dataset) compared to 81.9% with plain supervised learning.