Few-shot object detection, which aims at detecting novel objects rapidly from
extremely few annotated examples of previously unseen classes, has attracted
significant research interest in the community. Most existing approaches employ
the Faster R-CNN as basic detection framework, yet, due to the lack of tailored
considerations for data-scarce scenario, their performance is often not
satisfactory. In this paper, we look closely into the conventional Faster R-CNN
and analyze its contradictions from two orthogonal perspectives, namely
multi-stage (RPN vs. RCNN) and multi-task (classification vs. localization). To
resolve these issues, we propose a simple yet effective architecture, named
Decoupled Faster R-CNN (DeFRCN). To be concrete, we extend Faster R-CNN by
introducing Gradient Decoupled Layer for multi-stage decoupling and
Prototypical Calibration Block for multi-task decoupling. The former is a novel
deep layer with redefining the feature-forward operation and gradient-backward
operation for decoupling its subsequent layer and preceding layer, and the
latter is an offline prototype-based classification model with taking the
proposals from detector as input and boosting the original classification
scores with additional pairwise scores for calibration. Extensive experiments
on multiple benchmarks show our framework is remarkably superior to other
existing approaches and establishes a new state-of-the-art in few-shot
literature.

本文提出了一种名为 Decoupled Faster R-CNN (DeFRCN) 的简单而有效的体系结构，通过引入 Gradient Decoupled Layer 和 Prototypical Calibration Block 来解决数据稀少场景下的性能问题，在多个基准测试中都表现出优秀的性能表现，并成为少样本文献领域的新的最佳模型。