The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index; 4 of the 7 sources its claims cite were checked for support.
Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers
Open accessAbstract
Automated recognition of celestial bodies from observational imagery is a cornerstone of autonomous space exploration. However, deploying deep learning models in space environments entails rigorous requirements not only for accuracy but also for reliability (calibration) and safety (anomaly rejection). Traditional Convolutional Neural Networks (CNNs) trained on small-scale astronomical datasets often suffer from overfitting and overconfidence on Out-of-Distribution (OOD) artifacts. In this work, we present a robust classification framework based on DINOv2, a Vision Transformer pre-trained via discriminative self-supervised learning. We curate a high-fidelity dataset of seven planetary classes sourced from NASA archives and propose a two-stage domain adaptation strategy to transfer large-scale foundation model features to this fine-grained task. Extensive experiments show that our method reaches 100% Top-1 accuracy on the canonical split, and remains highly stable under split variation, achieving 99.43% ± 0.85% Top-1 accuracy across R = 5 repeated stratified splits. More importantly, we address the critical issue of model trustworthiness. Through post hoc temperature scaling, our model achieves a state-of-the-art Expected Calibration Error (ECE) of 0.08%, representing a 36-fold improvement over ResNet50 (2.90%) and a 4.5-fold improvement over the EfficientNet-B3 baseline (0.36%). Furthermore, by integrating Energy-based OOD detection, the system effectively rejects non-planetary artifacts with an AUROC of 93.7%. Qualitative analysis using Grad-CAM reveals that self-supervised attention mechanisms naturally focus on intrinsic planetary features (e.g., surface textures and rings) while ignoring background noise, confirming the superior robustness of vision foundation models in astronomical vision tasks.
Overview
CoChat Summary
TL;DR
The paper proposes a two-stage DINOv2-based framework for classifying seven planetary classes from NASA imagery, adding post hoc temperature scaling and energy-based OOD detection for trustworthiness. It reports 100% Top-1 accuracy on the canonical split, 0.08% ECE after calibration, and 93.7% OOD AUROC, while stress tests identify Gaussian noise as the main robustness bottleneck.
Key findings
- DINOv2 achieved 100% Top-1 accuracy on the held-out test set, versus 96.2% for ResNet50; across 5 repeated stratified splits, a frozen-feature linear probe reached 99.43% ± 0.85% Acc@1.
- After temperature scaling, DINOv2 reached 0.08% ECE, compared with 0.36% for EfficientNet-B3 and 2.90% for ResNet50—reported as a 4.5-fold and 36-fold improvement, respectively.
- Energy-based OOD detection gave DINOv2 an AUROC of 93.7% (Table 1: 93.68%), versus ResNet50 at 86.8% (Table 1: 86.77%) and EfficientNet-B3 at 94.0% (Table 1: 93.96%).
- Stress tests on N = 105 showed clean accuracy of 100%; Gaussian noise reduced accuracy to 87.62% (σ = 5), 77.14% (σ = 10), and 68.57% (σ = 20), while blur, JPEG compression, downsampling, and cropping mostly stayed within 94.29–100%. RandAugment was critical: weak augmentation averaged 97.4% versus 100.0% with RandAugment.
Methods
- Dataset: manually curated 700 images across 7 classes (Earth, Jupiter, Mars, Moon, Neptune, Saturn, Uranus), 100 images per class, sourced from NASA archives; split 69:16:15 into 483 training, 112 validation, and 105 test images; OOD set of approximately 200 Google Image Search images; pHash verification found 0 exact or near-duplicates between training and test sets.
- Model and training: DINOv2 ViT-Base/14 via timm, with a two-stage transfer-learning strategy—Stage 1 linear probing (default 5 epochs) then Stage 2 selective fine-tuning of the last 4 blocks (default 20 epochs); AdamW with lr = 3 × 10⁻⁴ for Stage 1 and 3 × 10⁻⁵ for Stage 2, weight decay 1 × 10⁻⁴, early stopping patience 5, and RandAugment; baselines included ResNet50, EfficientNet-B3, ConvNeXt V2-Tiny, standard ViT-Base, and Swin Transformer, with OpenCLIP ViT-B-16 zero-shot accuracy of 84.76%.
- Evaluation: Top-1/Top-5 accuracy, macro-F1, balanced accuracy, Wilson and bootstrap confidence intervals, temperature scaling fitted on validation logits, ECE with 15 bins, TTA via flips, energy-based OOD AUROC and TPR at fixed FPR, Grad-CAM visualization, and controlled stress-test perturbations.
Limitations
- Stated: the curated dataset is small and balanced (700 images, 7 classes), so clean-test accuracy saturates for several modern architectures; the authors note this is not a fully realistic model of long-tailed operational astronomy data.
- Stated: the OOD set is sourced from web images and does not fully cover mission-specific sensor artifacts such as cosmic-ray hits, saturation spikes, and instrument-dependent noise; reported AUROC is therefore a web-image OOD benchmark rather than a definitive mission-sensor estimate.
- Stated: DINOv2 has deployment costs—ViT-Base/14 has 86M parameters, about 344 MB in FP32, and at S = 518 uses 1369 tokens versus 256 tokens at S = 224, giving roughly 5.35× more tokens and 28.6× larger quadratic attention cost; no learning-rate scheduler is used, and the small test split (15 images per class) limits stability, with repeated-split frozen-feature OOD AUROC at only 61.50% ± 3.49%.
- Evident from the text: some reported comparisons are inconsistent—DINOv2’s OOD AUROC is described as 93.7% and “statistically comparable” to EfficientNet, while Table 1 lists EfficientNet-B3 slightly higher at 93.96%—and saturated clean accuracy limits discrimination among modern architectures.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures







Verification
Claims the paper makes
2 Valid · 1 Not valid · 1 Not checked · 93 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Models such as DINOv2 [7], Vision Transformers (ViT) [8], and Swin Transformers [9] have demonstrated outstanding transfer learning performance across a wide range of domains, often achieving state-of-the-art results with only minimal fine-tuning.”
§ Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers > 1.2. The Promise of Vision Foundation Models
What the sources say
- Supportedcites [7] Oquab, M., Darcet, T., Moutakanni, T., Vo, H.V., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). DINOv2: Learning robust visual features without supervision. arXiv. source
The citation to DINOv2 supports the DINOv2 portion of the sentence, not the separately cited ViT and Swin Transformer claims. Section 10 (page not provided) reports strong performance across a wide range of benchmarks without fine-tuning; the Introduction also describes transferable frozen features competitive with leading alternatives. (LLM, conf=0.93)
- Not matchedcites [8] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3–7). An image is worth 16×16 words: Transformers for image recognition at scale. Proceedings of the 9th International Conference on Learning Representations (ICLR), Virtual Event. Available online: https://openreview.net/forum?id=YicbFdNTTy.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Partly supportedcites [9] Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 11-17 October 2021, IEEE. sourceExperimental — accuracy not yet measured
The Abstract reports that Swin Transformer surpasses previous state-of-the-art results on COCO object detection and ADE20K semantic segmentation, supporting strong performance across several vision tasks. It does not establish performance across a wide range of domains or with minimal fine-tuning; Appendix A2.2–A2.3 describes substantial task-specific training. (LLM, conf=0.87)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“but the model's effectiveness on scientific imaging domains with distinct statistical properties remains underexplored.”
§ Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers > 2.1. Vision Transformers and Foundation Models
What the sources say
- Could not verifycites [7] Oquab, M., Darcet, T., Moutakanni, T., Vo, H.V., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). DINOv2: Learning robust visual features without supervision. arXiv. sourceExperimental — accuracy not yet measured
The Out-of-distribution generalization section evaluates transfer using examples such as animal photographs and paintings, while Table 6 reports other domain-generalization benchmarks. Our copy does not address DINOv2’s effectiveness on scientific imaging or say that this setting remains underexplored (searched for scientific imaging, medical imaging, microscopy, and related domains). (LLM, conf=0.72)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we curated a class-balanced subset (100 images per class; 700 images total).”
§ Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers > 3.1.1. The Celestial Body Dataset
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we manually curated a high-fidelity Celestial Body Dataset as shown in Figure 2.”
§ Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers > 3.1.1. The Celestial Body Dataset
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the system effectively rejects non-planetary artifacts with an AUROC of 93.7%”
- Also stated in: § 1.4. Key Findings · plain
“our method achieves an AUROC of 93.7%”
§ Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 1.4. Key Findings · plain
48 more claims
Create a free account to see all 97 claims and every source verdict.
- Probably not a substantial claim. 24
- It may state two separate claims as one. 25
- The quote only partly states this claim. 3
Citations
Cites
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 3,111
Swin Transformer V2: Scaling Up Capacity and Resolution
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01170 · Cited by 2,484
DINOv2: Learning Robust Visual Features without Supervision
Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.07193 · Cited by 1,078
Generalized Out-of-Distribution Detection: A Survey
Yang, J., Zhou, K., Li, Y., & Liu, Z. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02117-4 · Cited by 884
Rotation-invariant convolutional neural networks for galaxy morphology prediction
Dieleman, S., Willett, K. W., & Dambre, J. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv632 · Cited by 781
Data mining and machine learning in astronomy
BALL, N. M., & BRUNNER, R. J. (2010) · International Journal of Modern Physics D · doi:10.1142/s0218271810017160 · Cited by 383
Foundation Models Defining a New Era in Vision: A Survey and Outlook
Awais, M., Naseer, M., Khan, S., Anwer, R. M., Cholakkal, H., Shah, M., Yang, M.-H., & Khan, F. S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3506283 · Cited by 304
Transfer learning for medical images analyses: A survey
Yu, X., Wang, J., Hong, Q.-Q., Teku, R., Wang, S.-H., & Zhang, Y.-D. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.08.159 · Cited by 232
Research works printed but not linked: 1
- Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3–7). An image is worth 16×16 words: Transformers for image recognition at scale. Proceedings of the 9th International Conference on Learning Representations (ICLR), Virtual Event. Available online: https://openreview.net/forum?id=YicbFdNTTy.
Metadata
- Authors
- Xu, Z., Choi, Y., Yi, C., Park, C., Park, J., Park, H., & Song, S.
- Affiliations
- Kyungpook National University (KR)
- Earth Turbine, 36, Dongdeok-ro 40-gil, Jung-gu, Daegu 41905, Republic of Korea
- Intelligent Construction Automation Center, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Republic of Korea
- Corresponding author
- Choi, Young
- Yi, Changyong
- Venue
- Aerospace
- Publisher
- MDPI AG
- Published
- 2026-02-27
- Volume
- 13
- Issue
- 3
- Pages
- 222
- ISSN
- 2226-4310 (ISSN-L)
- OpenAlex
- W7131846472
- Semantic Scholar
- 21947db5cd3e187082affbcd2fc64d587d57375d
- Cited by
- 0
- References
- 17
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Aerospace (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Ministry of Education (RS-2023-00249407)
- Korea government (RS-2024-00336025, RS-2025-00558871)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- planetary classification, self-supervised vision transformers, DINOv2, out-of-distribution detection, temperature scaling, calibration, domain adaptation, foundation models, celestial imagery, Grad-CAM
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers. https://app.cochat.ai/papers/10.3390/aerospace13030222
- The paper
- Xu, Z., Choi, Y., Yi, C., Park, C., Park, J., Park, H., & Song, S. (2026). Trustworthy Celestial Eye: Calibrated and Robust Planetary Classification via Self-Supervised Vision Transformers. Aerospace. https://doi.org/10.3390/aerospace13030222
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.