딥러닝 탐구생활

논문 출처 : https://arxiv.org/abs/2004.10934 YOLOv4: Optimal Speed and Accuracy of Object DetectionThere are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operatearxiv.org IntroductionCNN 기반 객체 감지기는 주로 추천 시스템에..

논문 출처 : https://arxiv.org/abs/1804.02767 YOLOv3: An Incremental ImprovementWe present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3arxiv.org YOLOv3(You Only Look Once version 3)는 Joseph Redmon과 Ali ..

논문 출처 : https://arxiv.org/abs/1612.08242 YOLO9000: Better, Faster, StrongerWe introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2,arxiv.org YOLOv2(You Only Look Once version 2)는 YOLO 모델의 개선된 버전으로, 2..