Novelty detection in rover-based planetary surface images using autoencoders
Bibliographic record
Abstract
In the domain of planetary science, novelty detection is gaining attention because of the operational opportunities it offers, including annotated data products and downlink prioritization. Using a variational autoencoder (VAE), this work improves upon state-of-the-art novelty detection performance in the context of Martian exploration by <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="m1"><mml:mo>></mml:mo><mml:mn>7</mml:mn><mml:mi>%</mml:mi></mml:math> (measured by the area under the receiver operating characteristic curve (ROC AUC)). Autoencoders, especially VAEs, perform well across all classes of novelties defined for Martian exploration. VAEs are shown to have high recall in the Martian context, making them particularly useful for on-ground processing. Convolutional autoencoders (CAEs), on the other hand, demonstrate high precision making them good candidates for onboard downlink prioritization. In our implementation adversarial autoencoders (AAEs) are also shown to perform on par with state-of-the-art. Dimensionality reduction is a key feature of autoencoders for novelty detection. In this study the impact of dimensionality reduction on detection quality is explored, showing that both VAEs and AAEs achieve comparable ROC AUCs to CAEs despite observably poorer (blurred) image reconstructions; this is observed both in Martian data and in lunar analogue data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".