[Paper Review] Object Detection
1.Precision-Recall Curve, mAP
Confusion Matrix : IoU(Intersectino over Union) : bounding box가 맞는지 틀린지를 결정하기 위한 지표.(출처 : https://www.v7labs.com/blog/mean-average-precision)I
2.[Simple Review] Region-based Convolutional Networks for Accurate Object Detection and Segmentation
R. Girshick, J. Donahue, T. Darrell and J. Malik, "Region-Based Convolutional Networks for Accurate Object Detection and Segmentation," in IEEE Transa
3.[Simple Review] Fast R-CNN
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:
4.Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
paper : Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networksauthors : Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sunsubmi
5.(YOLOv1) You Only Look Once : Unified, Real-Time Object Detection
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
6.[Simple Review] (YOLO9000, YOLOv2) YOLO9000: Better, Faster, Stronger
paper : YOLO9000: Better, Faster, Strongerauthor : Joseph Redmon, Ali Farhadisubject : 2017 IEEE Conference on Computer Vision and Pattern Recognition
7.[Simple Review] (YOLOv3) YOLOv3: An Incremental Improvement
paper : YOLOv3: An Incremental Improvementauthor : Joseph Redmon, Ali Farhadisubject : 나는 YOOLO에 대한 몇가지 improvement를 다뤘었다.하지만 이 논문에서는 super interestin
8.(FPN) Feature Pyramid Network for Object Detection
paper : Feature Pyramid Networks for Object Detectionauthor : Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie
9.(YOLOv4) YOLOv4: Optimal Speed and Accuracy of Object Detection
paper : YOLOv4: Optimal Speed and Accuracy of Object Detectionauthor : Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liaosubject : CVPR 2020CNN a
10.Prerequisite Knowledge for Reading the YOLOv4 Paper
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
11.(RetinaNet) Focal Loss for Dense Object Detection
paper : Focal Loss for Dense Object Detectionauthor : Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollársubject : 2017 IEEE Internatio
12.EfficientDet: Scalable and Efficient Object Detection
Tan, Mingxing, Ruoming Pang, and Quoc V. Le. "Efficientdet: Scalable and efficient object detection." Proceedings of the IEEE/CVF conference on comput
13.RTMDet: An Empirical Study of Designing Real-Time Object Detectors
https://arxiv.org/abs/2212.07784Lyu, Chengqi, et al. "Rtmdet: An empirical study of designing real-time object detectors." arXiv preprint arXiv:2
14.YOLOv10: Real-Time End-to-End Object Detection
https://github.com/THU-MIG/yolov10Wang, Ao, et al. "Yolov10: Real-time end-to-end object detection." arXiv preprint arXiv:2405.14458 (2024).
15.[DETR] End-to-End Object Detection with Transformers
제목 : End-to-End Object Detection with Transformers저자 : Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey
16.[Deformable DETR] Deformable DETR: Deformable Transformers for End-to-End Object Detection
RT-DETR을 읽으려고 하니, RT-DETR의 efficient hybrid encoder의 등장배경과 이해를 위해Deformable DETR에서 소개한 multi-scale Transformer encoder를 알아야 할 것 같아서Deformable DETR을 간략
17.[RT-DETR] DETRs Beat YOLOs on Real-time Object Detection
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
18.[DETR] > [Deformable DETR] > [RT DETR]
DETR variants들의 흐름과 해당 논문들에 대한 내용을 요약object detection은 object의 (bounding box, category label)이라는 set을 예측하는 것.이전의 object detector들은 이러한 set prediction
19.YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
https://openaccess.thecvf.com/content/CVPR2023/html/Wang_YOLOv7_Trainable_Bag-of-Freebies_Sets_New_State-of-the-Art_for_Real-Time_Object_Detector