In order to alleviate the scale variation problem in object detection, many feature pyramid networks are developed. In this paper, we rethink the issues existing in current methods and design a more effective module for feature fusion, called multiflow feature fusion module (MF³M). We first construct gate modules and multiple information flows in MF³M to avoid information redundancy and enhance the completeness and accuracy of information transfer between feature maps. Furtherore, in order to reduce the discrepancy of classification and regression in object detection, a modified deformable convolution which is termed task adaptive convolution (TaConv) is proposed in this study. Different offsets and masks are predicted to achieve the disentanglement of features for classification and regression in TaConv. By integrating the above two designs, we build a novel feature pyramid network with feature fusion and disentanglement (FFAD) which can mitigate the scale misalignment and task misalignment simultaneously. Experimental results show that FFAD can boost the performance in most models.

中文翻译：

---

用于目标检测的具有特征融合和解缠结的新型金字塔网络

为了缓解目标检测中的尺度变化问题，开发了许多特征金字塔网络。在本文中，我们重新思考当前方法中存在的问题，并设计了一种更有效的特征融合模块，称为多流特征融合模块（MF ³ M）。^{我们首先在 MF 3} M中构建门模块和多个信息流，以避免信息冗余并增强特征图之间信息传递的完整性和准确性。此外，为了减少目标检测中分类和回归的差异，本研究提出了一种改进的可变形卷积，称为任务自适应卷积（TaConv）。预测不同的偏移量和掩码以实现 TaConv 中分类和回归的特征解开。通过整合上述两种设计，我们构建了一种具有特征融合和解缠（FFAD）的新型特征金字塔网络，可以同时减轻尺度错位和任务错位。实验结果表明，FFAD 可以提高大多数模型的性能。