[Paper Review] 2D Object Detection

Confusion Matrix : IoU(Intersectino over Union) : bounding box가 맞는지 틀린지를 결정하기 위한 지표.(출처 : https://www.v7labs.com/blog/mean-average-precision)I

R. Girshick, J. Donahue, T. Darrell and J. Malik, "Region-Based Convolutional Networks for Accurate Object Detection and Segmentation," in IEEE Transa

paper : Fast R-CNNauthor : Ross Girshicksubject : CVPR 2015Fast R-CNN의 base가 R-CNN인데, 직접 읽지 않고 간략히 내용만 파악함R-CNN 내용 파악을 위해 읽은 paper review :https:

paper : Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networksauthors : Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sunsubmi

Info Abstract 1. Introduction 2. Unified Detection 2.1. Network Design 2.2. Training 2.3. Inference 2.4. Limitations of YOLO 3. Comparison to Ot

paper : YOLO9000: Better, Faster, Strongerauthor : Joseph Redmon, Ali Farhadisubject : 2017 IEEE Conference on Computer Vision and Pattern Recognition

paper : Focal Loss for Dense Object Detectionauthor : Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollársubject : 2017 IEEE Internatio

paper : YOLOv3: An Incremental Improvementauthor : Joseph Redmon, Ali Farhadisubject : 나는 YOOLO에 대한 몇가지 improvement를 다뤘었다.하지만 이 논문에서는 super interestin

paper : YOLOv4: Optimal Speed and Accuracy of Object Detectionauthor : Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liaosubject : CVPR 2020CNN a

자료 참고, 출처 :https://www.youtube.com/watch?v=D6mj_T8K_bo&t=293shttps://wikidocs.net/163049이 사전 지식들의 original paper를 모두 읽진 않고, 어떠한 아이디어인지만 간략하게

제목 : End-to-End Object Detection with Transformers저자 : Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey

RT-DETR을 읽으려고 하니, RT-DETR의 efficient hybrid encoder의 등장배경과 이해를 위해Deformable DETR에서 소개한 multi-scale Transformer encoder를 알아야 할 것 같아서Deformable DETR을 간략

이 paper에서 a novel query formulation using dynamic anchor boxes for DETR을 소개하고a deepr understanding of the role in queries in DETR을 제공한다.This new formu

https://arxiv.org/abs/2212.07784Lyu, Chengqi, et al. "Rtmdet: An empirical study of designing real-time object detectors." arXiv preprint arXiv:2

https://openaccess.thecvf.com/content/CVPR2023/html/Wang_YOLOv7_Trainable_Bag-of-Freebies_Sets_New_State-of-the-Art_for_Real-Time_Object_Detector

Paper Info Wenyu Lv, Yian Zhao, Shangliang Xu, Jinman Wei, Guanzhong Wang, Cheng Cui, Yuning Du, Qingqing Dang, Yi Liu Baidu Inc. "Detrs beat yolos o

DETR variants들의 흐름과 해당 논문들에 대한 내용을 요약object detection은 object의 (bounding box, category label)이라는 set을 예측하는 것.이전의 object detector들은 이러한 set prediction

https://github.com/THU-MIG/yolov10Wang, Ao, et al. "Yolov10: Real-time end-to-end object detection." arXiv preprint arXiv:2405.14458 (2024).

현재 NeurIPS 2025 main conference에 poster로 accept되었지만, 아직 publish 전이라 ArXiv에 있는 technical report로 리뷰.(배경)YOLO framework의 the network architecture 향상은 오랜