Feature upsampling is a key operation in a number of modern convolutional network architectures, e.g. feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose Content-Aware ReAssembly of FEatures (CARAFE), a universal, lightweight and highly effective operator to fulfill this goal. CARAFE has several appealing properties: (1) Large field of view. Unlike previous works (e.g. bilinear interpolation) that only exploit sub-pixel neighborhood, CARAFE can aggregate contextual information within a large receptive field. (2) Content-aware handling. Instead of using a fixed kernel for all samples (e.g. deconvolution), CARAFE enables instance specific content-aware handling, which generates adaptive kernels on-the-fly. (3) Lightweight and fast to compute. CARAFE introduces little computational overhead and can be readily integrated into modern network architectures. We conduct comprehensive evaluations on standard benchmarks in object detection, instance/semantic segmentation and inpainting. CARAFE shows consistent and substantial gains across all the tasks (1.2%, 1.3%, 1.8%, 1.1db respectively) with negligible computational overhead. It has great potential to serve as a strong building block for future research.

本文提出Content-Aware ReAssembly of FEatures（CARAFE）操作符，用于对象检测和语义/实例分割中的及时高效特征上采样，它有较大的视野和上下文感知处理能力，计算轻量且能够无缝地集成到现代网络架构中，并在标准基准测试中取得了显著改进，代码和模型在 https URL中可用。

CARAFE: 内容感知特征重组