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/smallsunsun1/custom_ops

CARAFE: Content-Aware ReAssembly of FEatures

https://github.com/smart-car-lab/Centernet2-mmdetction

Probabilistic two-stage detection

https://github.com/smc-x/ms-resnetv2

Deep Residual Learning for Image Recognition

https://github.com/smichalowski/faster_rcnn

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

https://github.com/smilingwolf/sw-cv-modelzoo

Bag of Tricks for Image Classification with Convolutional Neural Networks

https://github.com/smin107/CapstoneDesign

YOLOv4: Optimal Speed and Accuracy of Object Detection

https://github.com/smitheric95/MoCoViT-PyTorch

MoCoViT: Mobile Convolutional Vision Transformer

https://github.com/snilloO/obj_det_loss

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

https://github.com/snilloO/wheat_det

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

https://github.com/soccergame/darknet

YOLO9000: Better, Faster, Stronger

https://github.com/soeaver/py-RFCN-priv

Feature Pyramid Networks for Object Detection

https://github.com/softbankrobotics-research/darknet_ros

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

https://github.com/sokeeffe/caffe_yolo

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

https://github.com/solapark/da_yolo

YOLO9000: Better, Faster, Stronger

https://github.com/solapark/darknet_interpark

YOLO9000: Better, Faster, Stronger

https://github.com/solapark/darknet_partdet

YOLO9000: Better, Faster, Stronger

https://github.com/solapark/darknet_partdet_tmp

YOLO9000: Better, Faster, Stronger

https://github.com/solaris33/YOLO-v1-tf2

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

https://github.com/sonamghosh/local_hack_day_2018

TextBoxes++: A Single-Shot Oriented Scene Text Detector

https://github.com/sonnguyen64/horus-tf-faster-rcnn

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

https://github.com/soo89/ISD-SSD

Interpolation-based semi-supervised learning for object detection

https://github.com/sophieloiz/brain-tissues-segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/soran-ghaderi/torchebm

Energy-Based Models for Deep Probabilistic Regression

https://github.com/sorg20/RPN

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

https://github.com/soribadiaby/Deep-Learning-liver-segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/soulguy/Faster-rcnn

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

https://github.com/soulslicer/staf

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

https://github.com/soumik12345/AODNet

An All-in-One Network for Dehazing and Beyond

https://github.com/soumik12345/RCNN

Rich feature hierarchies for accurate object detection and semantic segmentation

https://github.com/soumith/convnet-benchmarks

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

https://github.com/soumith/imagenet-multiGPU.torch

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

https://github.com/sourabhagrawal23/human-action-classification

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

https://github.com/souravverma94/pre_trained_imgclassifier_dogBreeds

Deep Residual Learning for Image Recognition

https://github.com/sovit-123/traffic-light-detection-using-yolov3

Detecting Traffic Lights by Single Shot Detection

https://github.com/sowit-labs/grassUNet

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/soxHenry433/TF2_U2Model

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

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