Papers with Code 아카이브

16k

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

6

평가표

1

보존된 평가 기록

1

코드

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

https://github.com/BonJunKu/ScooterHelmetDetector

You Only Look Once: Unified, Real-Time Object Detection

https://github.com/Booomshaker/SparseRCNNWSL

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

https://github.com/Bribak/DeepConnection

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

https://github.com/BrilliantYuKaimin/XCiT-PaddlePaddle

XCiT: Cross-Covariance Image Transformers

https://github.com/Brunogomes97/Imdb

Random Erasing Data Augmentation

https://github.com/BryanPlummer/Two_branch_network

Revisiting Image-Language Networks for Open-ended Phrase Detection

https://github.com/BryanPlummer/cite

Revisiting Image-Language Networks for Open-ended Phrase Detection

https://github.com/Build-Week-Spotify-Song-Suggester-5/Data-Science

Neural Nearest Neighbors Networks

https://github.com/BupyeongHealer/Mask_RCNN_tf_2.x

Mask R-CNN

https://github.com/Burf/EfficientNet-Lite-Tensorflow2

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/Burf/HRNetV2-OCR-Tensorflow2

High-Resolution Representations for Labeling Pixels and Regions

https://github.com/Burf/ResNeSt-Tensorflow2

ResNeSt: Split-Attention Networks

https://github.com/Burf/ResNet-Tensorflow2

Deep Residual Learning for Image Recognition

https://github.com/Burf/SwinTransformer-Tensorflow2

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

https://github.com/Burf/tfdetection

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

https://github.com/Burton2000/semantic_segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/C677/Machine-learning

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

https://github.com/CAMMA-public/ai4surgery

EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos

https://github.com/CAPTAIN-WHU/DOTA_devkit

DOTA: A Large-scale Dataset for Object Detection in Aerial Images

https://github.com/CASIA-IVA-Lab/ISP-reID

Deep High-Resolution Representation Learning for Human Pose Estimation

https://github.com/CMU-Perceptual-Computing-Lab/openpose

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

https://github.com/CMU-Perceptual-Computing-Lab/openpose_unity_plugin

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

https://github.com/CREVIOS/MediSinGAN

SinGAN: Learning a Generative Model from a Single Natural Image

https://github.com/CRIGIM/darknet

YOLOv3: An Incremental Improvement

https://github.com/CS-GangXu/TMNet

Deformable ConvNets v2: More Deformable, Better Results

https://github.com/CSAILVision/semantic-segmentation-pytorch

Pyramid Scene Parsing Network

https://github.com/CSAILVision/unifiedparsing

Acquisition of Localization Confidence for Accurate Object Detection

https://github.com/CSSFA123/yolov4-Road

Scaled-YOLOv4: Scaling Cross Stage Partial Network

https://github.com/CUAI-CAU/Computer_vision_team_1

You Only Look Once: Unified, Real-Time Object Detection

https://github.com/CV-Reimplementation/AEFNet-Reimplementation

Auto-Exposure Fusion for Single-Image Shadow Removal

https://github.com/CV-Reimplementation/BMNet-Reimplementation

https://github.com/CV-Reimplementation/DHAN-reimplementation

Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN

https://github.com/CV-Reimplementation/TraditionalDocumentShadowRemoval

Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal

https://github.com/CV-deeplearning/caffe

SSD: Single Shot MultiBox Detector

https://github.com/CV51GO/GFLv2_Megengine

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

https://github.com/CV51GO/HarDNet_Megengine

HarDNet: A Low Memory Traffic Network

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