2605.29539v1 May 28, 2026 cs.CV

GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection

Yixiong Zou
Yixiong Zou
Citations: 378
h-index: 10
Yaze Zhao
Yaze Zhao
Citations: 17
h-index: 2
Shuqi Luo
Shuqi Luo
Citations: 0
h-index: 0
Yikai Qin
Yikai Qin
Citations: 26
h-index: 3
Jia-chiam Liu
Jia-chiam Liu
Citations: 16
h-index: 1
Yong Jiang
Yong Jiang
Citations: 11
h-index: 1

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}.

0 Citations
0 Influential
25 Altmetric
125.0 Score
Original PDF
0

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!