Description
Content-Aware ReAssembly of FEatures (CARAFE) is an operator for feature upsampling in convolutional neural networks. CARAFE has several appealing properties: (1) Large field of view. Unlike previous works (e.g. bilinear interpolation) that only exploit subpixel 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.
Papers Using This Method
CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules2024-11-17Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels2024-10-29IDD-YOLOv5: A Lightweight Insulator Defect Real-time Detection Algorithm2024-08-19Learning to Upsample by Learning to Sample2023-08-29On the impact of using X-ray energy response imagery for object detection via Convolutional Neural Networks2021-08-27CARAFE: Content-Aware ReAssembly of FEatures2019-05-06