EUVIMEDEUVIMED entdecken
Crossref

Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization

Yan Huang, Yongyi Su, Xin Lin, Le Zhang, Xun Xu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5185-5193

DOI: 10.1609/aaai.v40i7.37433 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yan Huang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The emergence of foundation models has substantially advanced zero-shot generalization in monocular depth estimation (MDE), as exemplified by the Depth Anything series. However, given access to some data from downstream tasks, a natural question arises: can the performance of these models be further improved? To this end, we propose WeSTAR, a parameter-efficient framework that performs \textbf{We}akly supervised \textbf{S}elf-\textbf{T}raining \textbf{A}daptation with \textbf{R}egularization, designed to enhance the robustness of MDE foundation models in unseen and diverse domains. We first adopt a dense self-training objective as the primary source of structural self-supervision. To further improve robustness, we introduce semantically-aware hierarchical normalization, which exploits instance-level segmentation maps to perform more stable and multi-scale structural normalization. Beyond dense supervision, we introduce a cost-efficient weak supervision in the form of pairwise ordinal depth annotations to further guide the adaptation process, which enforces informative ordinal constraints to mitigate local topological errors. Finally, a weight regularization loss is employed to anchor the LoRA updates, ensuring training stability and preserving the model's generalizable knowledge. Extensive experiments on both realistic and corrupted out-of-distribution datasets under diverse and challenging scenarios demonstrate that WeSTAR consistently improves generalization and achieves state-of-the-art performance across a wide range of benchmarks.

Zitieren

APA

Huang, Y., Su, Y., Lin, X., Zhang, L., & Xu, X. (2026). Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5185-5193. https://doi.org/10.1609/aaai.v40i7.37433

Vancouver

Huang Y, Su Y, Lin X, Zhang L, Xu X. Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5185-5193. doi:10.1609/aaai.v40i7.37433

BibTeX
@article{Huang2026,
  author = {Huang, Yan and Su, Yongyi and Lin, Xin and Zhang, Le and Xu, Xun},
  title = {Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5185--5193},
  doi = {10.1609/aaai.v40i7.37433}
}
Kostenlos starten →