EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Few-Shot Mars Rover Onboard Surface Scene Classification Based on SE-ResNet-MTL

Yuheng He, Na Shen, Xiangjin Zhang, Zhiliang Wu, Jinghao Li, Dong Hou

Remote Sensing · 10.07.2026 · 18 (14) · 2319

DOI: 10.3390/rs18142319 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.07.2026. Verfasst von Yuheng He und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of limited annotated datasets, strong demand for few-shot adaptation, and insufficient feature representation of traditional backbone networks in Mars rover onboard surface scene classification, this study proposes a classification framework that integrates a channel attention mechanism with meta-transfer learning. The work consisted of two main components. First, a dedicated annotated dataset for core Mars rover onboard surface scenes was constructed based on publicly available Mars Science Laboratory (MSL) Mastcam RGB imagery, providing a standardized experimental benchmark. Second, a classification model was developed based on ResNet50. Transfer learning with ImageNet pre-trained weights was employed to improve feature initialization, and an Squeeze-and-Excitation (SE) attention module was incorporated to enhance channel-wise feature representation. Furthermore, an appropriate activation function was selected under engineering constraints. Finally, a meta-learning strategy based on Model-Agnostic Meta-Learning (MAML) was introduced to improve adaptation capability in few-shot scenarios. Experimental results showed that the SE-ResNet model achieved a validation accuracy of 95.52%, representing an improvement of 17.41% over the baseline model. After integrating meta-transfer learning, the proposed SE-ResNet-MTL (SE-Enhanced ResNet Meta-Transfer Learning) model achieved accuracies of 90.5% and 91.5% in 1-shot and 5-shot tasks, respectively, outperforming traditional fine-tuning methods by 42.8% and 25.4%. These improvements were obtained with only a 5.47% decrease in full-dataset accuracy. Overall, the proposed method effectively balances full-dataset performance and few-shot generalization, providing a practical and efficient solution for Mars rover onboard surface scene recognition and other extraterrestrial visual tasks.

Zitieren

APA

He, Y., Shen, N., Zhang, X., Wu, Z., Li, J., & Hou, D. (2026). Research on Few-Shot Mars Rover Onboard Surface Scene Classification Based on SE-ResNet-MTL. Remote Sensing, 18(14), 2319. https://doi.org/10.3390/rs18142319

Vancouver

He Y, Shen N, Zhang X, Wu Z, Li J, Hou D. Research on Few-Shot Mars Rover Onboard Surface Scene Classification Based on SE-ResNet-MTL. Remote Sensing. 2026;18(14):2319. doi:10.3390/rs18142319

BibTeX
@article{He2026,
  author = {He, Yuheng and Shen, Na and Zhang, Xiangjin and Wu, Zhiliang and Li, Jinghao and Hou, Dong},
  title = {Research on Few-Shot Mars Rover Onboard Surface Scene Classification Based on SE-ResNet-MTL},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {14},
  pages = {2319},
  doi = {10.3390/rs18142319}
}
Kostenlos starten →