Description
Fast R-CNN is an object detection model that improves in its predecessor R-CNN in a number of ways. Instead of extracting CNN features independently for each region of interest, Fast R-CNN aggregates them into a single forward pass over the image; i.e. regions of interest from the same image share computation and memory in the forward and backward passes.
Papers Using This Method
WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation2025-02-27How To Effectively Train An Ensemble Of Faster R-CNN Object Detectors To Quantify Uncertainty2023-10-07Classification of White Blood Cells Using Machine and Deep Learning Models: A Systematic Review2023-08-11Domain Adaptive Person Search via GAN-based Scene Synthesis for Cross-scene Videos2023-08-08Random Boxes Are Open-world Object Detectors2023-07-17CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics2022-07-02Classification of Phonological Parameters in Sign Languages2022-05-24CoVA: Context-aware Visual Attention for Webpage Information Extraction2021-10-24Anchor-free Oriented Proposal Generator for Object Detection2021-10-05DASHA: Decentralized Autofocusing System with Hierarchical Agents2021-08-29Densely-Populated Traffic Detection using YOLOv5 and Non-Maximum Suppression Ensembling2021-08-27A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets2021-07-16Object sorting using faster R-CNN2020-12-29Weakly Supervised Instance Segmentation by Deep Community Learning2020-01-30The Pedestrian Patterns Dataset2020-01-06Discriminative Feature Transformation for Occluded Pedestrian Detection2019-10-01Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution2019-09-15Fast and Efficient Model for Real-Time Tiger Detection In The Wild2019-09-03RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles2019-05-01Object-driven Text-to-Image Synthesis via Adversarial Training2019-02-27