Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances
Not on the map. Why?
Abstract (arXiv)
The NASA Planetary Data System hosts millions of images acquired from the planet Mars. To help users quickly find images of interest, we have developed and deployed content-based classification and search capabilities for Mars orbital and surface images. The deployed systems are publicly accessible using the PDS Image Atlas. We describe the process of training, evaluating, calibrating, and deploying updates to two CNN classifiers for images collected by Mars missions. We also report on three years of deployment including usage statistics, lessons learned, and plans for the future.
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 3 of its 25 references that are in the map. First posted on arXiv 9 Feb 2021.
Builds on
3 of 25 references.
References · 3
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
- 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
Built on by
Citing papers per year: 2022: 5; 2023: 1; 2024: 1; 2025: 1; 2026: 2.
10 papers.
- 2022Self-Supervised Learning to Guide Scientifically Relevant Categorization of Martian Terrain Imagescited by 5
- 2023ConeQuest: A Benchmark for Cone Segmentation on Marscited by 3
- 2022Explainability Tools Enabling Deep Learning in Future In-Situ Real-Time Planetary Explorationscited by 1
- 2022Using Machine Learning to Reduce Observational Biases When Detecting New Impacts on Marscited by 1
- 2022Improving Contrastive Learning on Visually Homogeneous Mars Rover Imagescited by 1
- 2025Enhancing Martian Terrain Recognition with Deep Constrained Clusteringcited by 1
- 2026Natural Language-Driven Global Mapping of Martian Landformscited by 1
- 2026MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applicationscited by 1
- 2022Mixed-domain Training Improves Multi-Mission Terrain Segmentationcited by 0
- 2024Interactive Mars Image Content-Based Search with Interpretable Machine Learningcited by 0
- 2026MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications3 Apr 2026
- 2026Natural Language-Driven Global Mapping of Martian Landforms22 Jan 2026
- 2025Enhancing Martian Terrain Recognition with Deep Constrained Clustering22 Mar 2025
- 2024Interactive Mars Image Content-Based Search with Interpretable Machine Learning19 Jan 2024
- 2023ConeQuest: A Benchmark for Cone Segmentation on Mars15 Nov 2023
- 2022Improving Contrastive Learning on Visually Homogeneous Mars Rover Images17 Oct 2022
- 2022Mixed-domain Training Improves Multi-Mission Terrain Segmentation27 Sep 2022
- 2022Using Machine Learning to Reduce Observational Biases When Detecting New Impacts on Mars12 Jul 2022
- 2022Self-Supervised Learning to Guide Scientifically Relevant Categorization of Martian Terrain Images21 Apr 2022
- 2022Explainability Tools Enabling Deep Learning in Future In-Situ Real-Time Planetary Explorations15 Jan 2022