论文标题
汽车++：统一的内容感知功能重新组装
CARAFE++: Unified Content-Aware ReAssembly of FEatures
论文作者
论文摘要
功能重新组装，即功能下采样和上采样，是许多现代卷积网络体系结构（例如残留网络和特征金字塔）中的关键操作。它的设计对于密集的预测任务至关重要，例如对象检测和语义/实例分段。在这项工作中，我们提出了统一的内容感知功能的重新组装（Carafe ++），这是一个实现这一目标的通用，轻巧且高效的操作员。汽车++具有几种吸引人的特性：（1）与传统方法（例如合并和插值）不同，这些方法仅利用子像素邻域，calafe ++在大型接受领域内汇总了上下文信息。 （2）玻璃瓶++不是对所有样品（例如卷积和反卷积）使用固定的内核，而是会在即时生成自适应核，以实现特定于实例的内容感知的处理。 （3）汽车++引入了很少的计算开销，并且可以容易地集成到现代网络架构中。我们在对象检测，实例/语义分割和图像插入中对标准基准进行全面评估。汽车++在所有任务（分别为2.5％的APBox，2.1％APMASK，1.94％MIOU，1.35 dB）中显示出一致且可观的收益，其计算开销可忽略不计。它显示出充当现代深网的强大基础的巨大潜力。
Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose unified Content-Aware ReAssembly of FEatures (CARAFE++), a universal, lightweight and highly effective operator to fulfill this goal. CARAFE++ has several appealing properties: (1) Unlike conventional methods such as pooling and interpolation that only exploit sub-pixel neighborhood, CARAFE++ aggregates contextual information within a large receptive field. (2) Instead of using a fixed kernel for all samples (e.g. convolution and deconvolution), CARAFE++ generates adaptive kernels on-the-fly to enable instance-specific content-aware handling. (3) 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 image inpainting. CARAFE++ shows consistent and substantial gains across all the tasks (2.5% APbox, 2.1% APmask, 1.94% mIoU, 1.35 dB respectively) with negligible computational overhead. It shows great potential to serve as a strong building block for modern deep networks.
