Papers with Code 아카이브

Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

39

평가표

124

보존된 평가 기록

977

코드

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

https://github.com/CoinCheung/denseCL

Dense Contrastive Learning for Self-Supervised Visual Pre-Training

https://github.com/CoinCheung/pytorch-loss/blob/master/pytorch_loss/iou_loss.py

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

https://github.com/ColdNoodler/py-faster-rcnn-cuda10

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

https://github.com/Coldestadam/DynamicHead

Dynamic Head: Unifying Object Detection Heads with Attentions

https://github.com/Coldmooon/RCNN-for-Latest-Caffe

Rich feature hierarchies for accurate object detection and semantic segmentation

https://github.com/Coldmooon/SSD-on-Custom-Dataset

SSD: Single Shot MultiBox Detector

https://github.com/Congpeiliang/yolo

YOLOv3: An Incremental Improvement

https://github.com/ConnorChristie/image-to-3d-bbox

3D Bounding Box Estimation Using Deep Learning and Geometry

https://github.com/CorneliusHsiao/FoodMethodGAN

Deep Residual Learning for Image Recognition

https://github.com/Cosmos218/ssd-caffe

SSD: Single Shot MultiBox Detector

https://github.com/CrossEntropy/Gesture-images-recognition-ResidualNetwork

Deep Residual Learning for Image Recognition

https://github.com/CryptoSalamander/pytorch_paper_implementation

Deep Residual Learning for Image Recognition

https://github.com/CuberrChen/STDCNet-Paddle

Rethinking BiSeNet For Real-time Semantic Segmentation

https://github.com/CuberrChen/VoxelNet

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

https://github.com/CuberrChen/efficientdet-paddle

EfficientDet: Scalable and Efficient Object Detection

https://github.com/CycloneBoy/PPDetectionPytorch

SSD: Single Shot MultiBox Detector

https://github.com/Cyprien0105/DataScience

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/D-X-Y/DXY-Projects/tree/master/MSPLD

Few-Example Object Detection with Model Communication

https://github.com/D-X-Y/ResNeXt-DenseNet

Deep Residual Learning for Image Recognition

https://github.com/D1vyansh/BodyJointDetection

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

https://github.com/DASHANANT/Video-Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/DCASE-REPO/dcase2019_task2_baseline

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

https://github.com/DChaushev/Age-Gender-Recognition

Max-Margin Object Detection

https://github.com/DHZS/tf-deformable-conv-layer

Deformable Convolutional Networks

https://github.com/DHZS/tf-dropblock

DropBlock: A regularization method for convolutional networks

https://github.com/DIG-Beihang/OPIXray

Occluded Prohibited Items Detection: an X-ray Security Inspection Benchmark and De-occlusion Attention Module

https://github.com/DIUx-xView/xView2_first_place

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/DInesh1234-wq/tyredataset

YOLO9000: Better, Faster, Stronger

https://github.com/DLWK/EANet

Rethinking Atrous Convolution for Semantic Image Segmentation

https://github.com/DS4SD/DocLayNet

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

https://github.com/DS4SD/docling

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

https://github.com/DT42/BerryNet

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

https://github.com/DableUTeeF/keras-efficientnet

Deep Residual Learning for Image Recognition

https://github.com/DaiJianBo/CenterNet-duan-2080Ti

CenterNet: Keypoint Triplets for Object Detection

https://github.com/DaikiTanak/manifold_mixup

Deep Residual Learning for Image Recognition

https://github.com/Daividao/semantic-segmentation-deeplearning

U-Net: Convolutional Networks for Biomedical Image Segmentation

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