Description
Receptive Field Block (RFB) is a module for strengthening the deep features learned from lightweight CNN models so that they can contribute to fast and accurate detectors. Specifically, RFB makes use of multi-branch pooling with varying kernels corresponding to RFs of different sizes, applies dilated convolution layers to control their eccentricities, and reshapes them to generate final representation.
Papers Using This Method
Improved YOLOv7 model for insulator defect detection2025-02-11Physics-informed CoKriging model of a redox flow battery2021-06-17Efficient Face Detection in the Fisheye Image Domain2021-06-14Perceptual Extreme Super Resolution Network with Receptive Field Block2020-05-26YOLOv4: Optimal Speed and Accuracy of Object Detection2020-04-23RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation2019-06-29FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange2019-05-24Receptive Field Block Net for Accurate and Fast Object Detection2017-11-21