Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.04517 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909568421855232 |
|---|---|
| author | Pan, Jiancheng Liu, Yanxing He, Xiao Peng, Long Li, Jiahao Sun, Yuze Huang, Xiaomeng |
| author_facet | Pan, Jiancheng Liu, Yanxing He, Xiao Peng, Long Li, Jiahao Sun, Yuze Huang, Xiaomeng |
| contents | Foundation models pretrained on extensive datasets, such as GroundingDINO and LAE-DINO, have performed remarkably in the cross-domain few-shot object detection (CD-FSOD) task. Through rigorous few-shot training, we found that the integration of image-based data augmentation techniques and grid-based sub-domain search strategy significantly enhances the performance of these foundation models. Building upon GroundingDINO, we employed several widely used image augmentation methods and established optimization objectives to effectively navigate the expansive domain space in search of optimal sub-domains. This approach facilitates efficient few-shot object detection and introduces an approach to solving the CD-FSOD problem by efficiently searching for the optimal parameter configuration from the foundation model. Our findings substantially advance the practical deployment of vision-language models in data-scarce environments, offering critical insights into optimizing their cross-domain generalization capabilities without labor-intensive retraining. Code is available at https://github.com/jaychempan/ETS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04517 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection Pan, Jiancheng Liu, Yanxing He, Xiao Peng, Long Li, Jiahao Sun, Yuze Huang, Xiaomeng Computer Vision and Pattern Recognition Artificial Intelligence Foundation models pretrained on extensive datasets, such as GroundingDINO and LAE-DINO, have performed remarkably in the cross-domain few-shot object detection (CD-FSOD) task. Through rigorous few-shot training, we found that the integration of image-based data augmentation techniques and grid-based sub-domain search strategy significantly enhances the performance of these foundation models. Building upon GroundingDINO, we employed several widely used image augmentation methods and established optimization objectives to effectively navigate the expansive domain space in search of optimal sub-domains. This approach facilitates efficient few-shot object detection and introduces an approach to solving the CD-FSOD problem by efficiently searching for the optimal parameter configuration from the foundation model. Our findings substantially advance the practical deployment of vision-language models in data-scarce environments, offering critical insights into optimizing their cross-domain generalization capabilities without labor-intensive retraining. Code is available at https://github.com/jaychempan/ETS. |
| title | Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.04517 |