GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913175605084160 |
|---|---|
| author | Liu, Jiacong Luo, Shu Qin, Yikai Zhao, Yaze Jiang, Yongwei Zou, Yixiong |
| author_facet | Liu, Jiacong Luo, Shu Qin, Yikai Zhao, Yaze Jiang, Yongwei Zou, Yixiong |
| contents | Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to sparse single-instance annotations, and severe overfitting under extremely limited target-domain samples. To address these issues, this paper proposes GiPL, an efficient two-branch training framework. In the first branch, we design an iterative pseudo-label self-training paradigm, which performs zero-shot inference on the support set to generate reliable pseudo-annotations, fuses them with ground-truth labels, and iteratively optimizes the model to fully exploit support set data. In the second branch, we introduce generative data augmentation pipeline using large vision-language models, which synthesizes domain-aligned, multi-object annotated images to enrich training samples and suppress overfitting. Extensive experiments on three challenging CD-FSOD datasets (RUOD, CARPK, CarDD) under 1/5/10-shot settings demonstrate that GiPL consistently outperforms state-of-the-art methods with significant performance gains. Code is available at \href{https://github.com/z-yaz/CDiscover}{CDiscover}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29539 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection Liu, Jiacong Luo, Shu Qin, Yikai Zhao, Yaze Jiang, Yongwei Zou, Yixiong Computer Vision and Pattern Recognition Artificial Intelligence Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to sparse single-instance annotations, and severe overfitting under extremely limited target-domain samples. To address these issues, this paper proposes GiPL, an efficient two-branch training framework. In the first branch, we design an iterative pseudo-label self-training paradigm, which performs zero-shot inference on the support set to generate reliable pseudo-annotations, fuses them with ground-truth labels, and iteratively optimizes the model to fully exploit support set data. In the second branch, we introduce generative data augmentation pipeline using large vision-language models, which synthesizes domain-aligned, multi-object annotated images to enrich training samples and suppress overfitting. Extensive experiments on three challenging CD-FSOD datasets (RUOD, CARPK, CarDD) under 1/5/10-shot settings demonstrate that GiPL consistently outperforms state-of-the-art methods with significant performance gains. Code is available at \href{https://github.com/z-yaz/CDiscover}{CDiscover}. |
| title | GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.29539 |