딥러닝 탐구생활

https://docs.ultralytics.com/models/yolo11/ YOLO11 🚀 NEWDiscover YOLO11, the latest advancement in state-of-the-art object detection, offering unmatched accuracy and efficiency for diverse computer vision tasks.docs.ultralytics.com OverviewYOLO11은 Ultralytics YOLO 시리즈의 최신 버전으로, 실시간 객체 탐지 분야에서 정확도, 속도, 효율성 측면에서 혁신을 이루었다. 이전 YOLO 버전들의 발전을 바탕으로, YOLO11은 아키텍처와 학습 방법에서 중요한 개선을 도입하여, 다양한 컴퓨터 비전 작업에 적..

https://arxiv.org/abs/2404.14687 Pegasus-v1 Technical ReportThis technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language. Pegasus-1 is designed to address the unique challenges posed by video data, such as interpreting sparxiv.org Abstract트웰브랩스(Twelve Labs)에서 발표한 동영상 콘텐츠 이해 및 자연어 상호작용에 특화된 멀티모달 언어 모델인 ..

https://arxiv.org/abs/1905.11946 EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksConvolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing narxiv.org오늘은 그 유명한 EfficientNet을 한번 리..

논문 출처: https://arxiv.org/abs/2405.14458 YOLOv10: Real-Time End-to-End Object DetectionOver the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the architectural designs, optimarxiv.org Abstract최근 몇 년 동안 YOLO는 real-time object detec..

논문 출처 : https://arxiv.org/abs/2207.02696 YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorsYOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPSarxiv.org Ab..

논문 출처 : https://arxiv.org/abs/2209.02976 YOLOv6: A Single-Stage Object Detection Framework for Industrial ApplicationsFor years, the YOLO series has been the de facto industry-level standard for efficient object detection. The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios. In this technical reportarxiv.org Abstract빠르게 발전..

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..

논문 출처 : https://arxiv.org/abs/1506.02640 You Only Look Once: Unified, Real-Time Object DetectionWe present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabiliarxiv.org Object Detection은 One-Stage-Detectio..