深入审视跨域少样本目标检测：微调至关重要且并行解码器有益
A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps
提出一种混合集成解码器，通过共享层级层后接多个并行解码器分支（分支使用继承或新初始化的去噪查询）来提升少样本微调时的泛化性，且不增加额外参数；配合平台感知学习率调度的统一渐进式微调框架，为跨域少样本目标检测提供了可复用的解码器设计与训练策略。
原文依据 we propose a hybrid ensemble decoder that enhances generalization during fine-tuning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论少样本目标检测（FSOD）因训练样本稀缺而导致优化不稳定和泛化能力有限，极具挑战性。为解决这些问题，我们提出了一种混合集成解码器，可在微调过程中增强泛化能力。受集成学习启发，该解码器包含一个共享层级层，后接多个并行解码器分支，每个分支采用从共享层继承或新初始化的去噪查询，以鼓励预测多样性。该设计充分利用预训练权重且不引入额外参数，所得多样化预测可有效集成以提升泛化性。我们进一步利用统一的渐进式微调框架与平台感知学习率调度，稳定优化并在无需复杂数据增强或大量超参数调优的情况下实现强少样本适应。在 CD-FSOD、ODinW-13 和 RF100-VL 上的大量实验验证了方法的有效性。值得注意的是，在包含 100 个跨领域数据集的 RF100-VL 上，我们的方法在 10 样本设置下平均性能达 41.9，显著优于近期方法 SAM3 的 35.7。我们进一步从 CD-FSOD 构建混合域测试集以评估对分布外（OOD）样本的鲁棒性，表明所提模块带来明显性能提升。这些结果凸显了所提方法的有效性、泛化性和鲁棒性。代码见：https://github.com/Intellindust-AI-Lab/FT-FSOD。
英文原文摘要 1640 字符
Few-shot object detection (FSOD) is challenging due to unstable optimization and limited generalization arising from the scarcity of training samples. To address these issues, we propose a hybrid ensemble decoder that enhances generalization during fine-tuning. Inspired by ensemble learning, the decoder comprises a shared hierarchical layer followed by multiple parallel decoder branches, where each branch employs denoising queries either inherited from the shared layer or newly initialized to encourage prediction diversity. This design fully exploits pretrained weights without introducing additional parameters, and the resulting diverse predictions can be effectively ensembled to improve generalization. We further leverage a unified progressive fine-tuning framework with a plateau-aware learning rate schedule, which stabilizes optimization and achieves strong few-shot adaptation without complex data augmentations or extensive hyperparameter tuning. Extensive experiments on CD-FSOD, ODinW-13, and RF100-VL validate the effectiveness of our approach. Notably, on RF100-VL, which includes 100 datasets across diverse domains, our method achieves an average performance of 41.9 in the 10-shot setting, significantly outperforming the recent approach SAM3, which obtains 35.7. We further construct a mixed-domain test set from CD-FSOD to evaluate robustness to out-of-distribution (OOD) samples, showing that our proposed modules lead to clear improvement gains. These results highlight the effectiveness, generalization, and robustness of the proposed method. Code is available at: https://github.com/Intellindust-AI-Lab/FT-FSOD.