Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.14238 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917088653737984 |
|---|---|
| author | Huang, Yan Su, Yongyi Lin, Xin Zhang, Le Xu, Xun |
| author_facet | Huang, Yan Su, Yongyi Lin, Xin Zhang, Le Xu, Xun |
| contents | 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 Weakly supervised Self-Training Adaptation with Regularization, 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14238 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization Huang, Yan Su, Yongyi Lin, Xin Zhang, Le Xu, Xun Computer Vision and Pattern Recognition Machine Learning 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 Weakly supervised Self-Training Adaptation with Regularization, 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. |
| title | Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2511.14238 |