Few-shot object detection (FSOD), an efficient method for addressing the severe data-hungry problem, has been extensively discussed. Current works have significantly advanced the problem in terms of model and data. However, the overall performance of most FSOD methods still does not fulfill the desired accuracy. In this paper we improve the FSOD model to address the severe issue of sample imbalance and weak feature propagation. To alleviate modeling bias from data-sufficient base classes, we examine the effect of decoupling the parameters for classes with sufficient data and classes with few samples in various ways. We design a base-novel categories decoupled DETR (DeDETR) for FSOD. We also explore various types of skip connection between the encoder and decoder for DETR. Besides, we notice that the best outputs could come from the intermediate layer of the decoder instead of the last layer; therefore, we build a unified decoder module that could dynamically fuse the decoder layers as the output feature. We evaluate our model on commonly used datasets such as PASCAL VOC and MSCOCO. Our results indicate that our proposed module could achieve stable improvements of 5% to 10% in both fine-tuning and meta-learning paradigms and has outperformed the highest score in recent works.

翻译：少样本目标检测（FSOD）作为一种应对严重数据匮乏问题的有效方法，已得到广泛探讨。现有工作在模型和数据方面显著推进了该问题的发展。然而，大多数FSOD方法的整体性能仍未达到预期的准确度。本文通过改进FSOD模型，以解决样本不平衡和特征传播薄弱等严峻问题。为缓解来自数据充足基类别的建模偏差，我们探讨了多种方式解耦数据充足类与样本稀少类参数的策略。我们构建了一种基类-新类解耦的DETR（DeDETR）用于少样本目标检测，并探索了DETR编码器与解码器之间的多种跳跃连接方式。此外，我们注意到最佳输出可能来自解码器的中间层而非最后一层，因此设计了一个统一解码器模块，能够动态融合解码器各层作为输出特征。我们在PASCAL VOC和MSCOCO等常用数据集上评估了模型。结果表明，所提模块在微调和元学习范式下均能实现5%至10%的稳定性能提升，并超越了近期工作中的最高得分。