Papers with Code 아카이브

2D Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

15

평가표

20

보존된 평가 기록

57

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/IdiosyncraticDragon/relief_rcnn

Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection

https://github.com/IgorMunizS/mobileDet

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

https://github.com/IgorSusmelj/barlowtwins

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

https://github.com/IgorZaton/Mini-Projects

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/IliasMAOUDJ/dataset_gen

Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection

https://github.com/IlliaOvcharenko/lung-segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/IlyaDobrynin/GridMixup

GridMask Data Augmentation

https://github.com/IlyaOvodov/AngelinaReader

Focal Loss for Dense Object Detection

https://github.com/ImagingLab/Colorizing-with-GANs

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/Information-Fusion-Lab-Umass/Salient-Pedestrian-Detection

Pedestrian Detection in Thermal Images using Saliency Maps

https://github.com/InquisitiveOjas/Object-Detection_SSD

SSD: Single Shot MultiBox Detector

https://github.com/Instinct323/wiou/blob/v2/iou.py

Focal and Efficient IOU Loss for Accurate Bounding Box Regression

https://github.com/Iqbal1282/YoloV3

Soft-NMS -- Improving Object Detection With One Line of Code

https://github.com/Iqbal1282/yolov3_incremental_distillation_loss

YOLOv3: An Incremental Improvement

https://github.com/IsHYuhi/ST-CGAN_Stacked_Conditional_Generative_Adversarial_Networks

Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal

https://github.com/IsaacPatole/TGS-Salt-Identification-Challenge

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/Ivan-LZY/SG-Cyclingscapes

The Cityscapes Dataset for Semantic Urban Scene Understanding

https://github.com/IyatomiLab/CE-CLCNN

Random Erasing Data Augmentation

https://github.com/J-jjj7230/u-net_model

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/JC1DA/yolo_streamer

YOLOv4: Optimal Speed and Accuracy of Object Detection

https://github.com/JCamERG/YOLOPersonal

YOLOv3: An Incremental Improvement

https://github.com/JContro/pytorch_projects

Deep Residual Learning for Image Recognition

https://github.com/JDAI-CV/CoTNet

Contextual Transformer Networks for Visual Recognition

https://github.com/JDAI-CV/CoTNet-ObjectDetection-InstanceSegmentation

Contextual Transformer Networks for Visual Recognition

https://github.com/JDAI-CV/DCL

Look-into-Object: Self-supervised Structure Modeling for Object Recognition

https://github.com/JEFfersusu/RT-DSAFDet

Real-Time Dynamic Scale-Aware Fusion Detection Network: Take Road Damage Detection as an example

https://github.com/JEONGHA-SHIN/YOGO_Server_v2

YOLOv3: An Incremental Improvement

https://github.com/JHKim-snu/PGA

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

https://github.com/JHLee0513/Salt_detection_challenge

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/JHuang-CV/OD

MMDetection: Open MMLab Detection Toolbox and Benchmark

https://github.com/JHuang-CV/mmdetectionV2

MMDetection: Open MMLab Detection Toolbox and Benchmark

https://github.com/JIA-HONG-CHU/Swin-Transformer-add-EncNet-DaNet-DraNet-for-semantic-segmentation-on-Statelite-Dataset

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

https://github.com/JIHOO97/Image-Classification-Competition

Bag of Tricks for Image Classification with Convolutional Neural Networks

https://github.com/JKingKong/mmdetection

MMDetection: Open MMLab Detection Toolbox and Benchmark

https://github.com/JKmopl-code/SiamFC

Fully-Convolutional Siamese Networks for Object Tracking

https://github.com/JONGSKY/paper

Deep Residual Learning for Image Recognition

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.