From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912616611315712 |
|---|---|
| author | Xia, Changliang Jia, Chengyou Dang, Zhuohang Luo, Minnan Li, Zhihui Chang, Xiaojun |
| author_facet | Xia, Changliang Jia, Chengyou Dang, Zhuohang Luo, Minnan Li, Zhihui Chang, Xiaojun |
| contents | Dense prediction tasks hold significant importance of computer vision, aiming to learn pixel-wise annotated labels for input images. Despite advances in this field, existing methods primarily focus on idealized conditions, exhibiting limited real-world generalization and struggling with the acute scarcity of real-world data in practical scenarios. To systematically study this problem, we first introduce DenseWorld, a benchmark spanning a broad set of 25 dense prediction tasks that correspond to urgent real-world applications, featuring unified evaluation across tasks. We then propose DenseDiT, which exploits generative models' visual priors to perform diverse real-world dense prediction tasks through a unified strategy. DenseDiT combines a parameter-reuse mechanism and two lightweight branches that adaptively integrate multi-scale context. This design enables DenseDiT to achieve efficient tuning with less than 0.1% additional parameters, activating the visual priors while effectively adapting to diverse real-world dense prediction tasks. Evaluations on DenseWorld reveal significant performance drops in existing general and specialized baselines, highlighting their limited real-world generalization. In contrast, DenseDiT achieves superior results using less than 0.01% training data of baselines, underscoring its practical value for real-world deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20279 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios Xia, Changliang Jia, Chengyou Dang, Zhuohang Luo, Minnan Li, Zhihui Chang, Xiaojun Computer Vision and Pattern Recognition Dense prediction tasks hold significant importance of computer vision, aiming to learn pixel-wise annotated labels for input images. Despite advances in this field, existing methods primarily focus on idealized conditions, exhibiting limited real-world generalization and struggling with the acute scarcity of real-world data in practical scenarios. To systematically study this problem, we first introduce DenseWorld, a benchmark spanning a broad set of 25 dense prediction tasks that correspond to urgent real-world applications, featuring unified evaluation across tasks. We then propose DenseDiT, which exploits generative models' visual priors to perform diverse real-world dense prediction tasks through a unified strategy. DenseDiT combines a parameter-reuse mechanism and two lightweight branches that adaptively integrate multi-scale context. This design enables DenseDiT to achieve efficient tuning with less than 0.1% additional parameters, activating the visual priors while effectively adapting to diverse real-world dense prediction tasks. Evaluations on DenseWorld reveal significant performance drops in existing general and specialized baselines, highlighting their limited real-world generalization. In contrast, DenseDiT achieves superior results using less than 0.01% training data of baselines, underscoring its practical value for real-world deployment. |
| title | From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.20279 |