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/MindSpore-paper-code-3/code4/tree/main/googlenet

Going Deeper with Convolutions

https://github.com/MindSpore-paper-code-3/code4/tree/main/hardnet

HarDNet: A Low Memory Traffic Network

https://github.com/MindSpore-paper-code-3/code4/tree/main/hed

HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline

https://github.com/MindSpore-paper-code-3/code5/tree/main/RefineDet

Development of Fast Refinement Detectors on AI Edge Platforms

https://github.com/MindSpore-paper-code-3/code5/tree/main/ResNeXt

Res2Net: A New Multi-scale Backbone Architecture

https://github.com/MindSpore-paper-code-3/code5/tree/main/SE_ResNeXt50

Squeeze-and-Excitation Networks

https://github.com/MindSpore-paper-code-3/code5/tree/main/Segformer

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

https://github.com/MindSpore-paper-code-3/code5/tree/main/SemanticHumanMatting

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

https://github.com/MindSpore-paper-code-3/code5/tree/main/relationnet

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

https://github.com/MindSpore-paper-code-3/code5/tree/main/res2net_deeplabv3

Res2Net: A New Multi-scale Backbone Architecture

https://github.com/MindSpore-paper-code-3/code5/tree/main/res2net_faster_rcnn

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

https://github.com/MindSpore-paper-code-3/code5/tree/main/res2net_yolov3

YOLOv3: An Incremental Improvement

https://github.com/MindSpore-paper-code-3/code5/tree/main/resnet50_adv_pruning

Deep Residual Learning for Image Recognition

https://github.com/MindSpore-paper-code-3/code5/tree/main/resnetv2_50_frn

Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks

https://github.com/MindSpore-paper-code-3/code5/tree/main/retinanet_resnet101

Focal Loss for Dense Object Detection

https://github.com/MindSpore-paper-code-3/code5/tree/main/retinanet_resnet152

Focal Loss for Dense Object Detection

https://github.com/MindSpore-paper-code-3/code5/tree/main/rfcn

R-FCN: Object Detection via Region-based Fully Convolutional Networks

https://github.com/MindSpore-paper-code-3/code6/tree/main/CBAM

CBAM: Convolutional Block Attention Module

https://github.com/MindSpore-paper-code-3/code6/tree/main/CascadeRCNN

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

https://github.com/MindSpore-paper-code-3/code6/tree/main/adelaide_ea

FCOS: Fully Convolutional One-Stage Object Detection

https://github.com/MindSpore-paper-code-3/code6/tree/main/augvit

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

https://github.com/MindSpore-paper-code-3/code6/tree/main/centernet

CenterNet: Keypoint Triplets for Object Detection

https://github.com/MindSpore-paper-code-3/code6/tree/main/centernet_det

CenterNet: Keypoint Triplets for Object Detection

https://github.com/MindSpore-paper-code-3/code6/tree/main/centernet_resnet50_v1

CenterNet++ for Object Detection

https://github.com/MindSpore-paper-code-3/code6/tree/main/cnnctc

Fast R-CNN

https://github.com/MindSpore-paper-code-3/code6/tree/main/convnext

Global Context Vision Transformers

https://github.com/MindSpore-paper-code-3/code7/tree/main/FCANet

FcaNet: Frequency Channel Attention Networks

https://github.com/MindSpore-paper-code-3/code7/tree/main/FCOS

NAS-FCOS: Fast Neural Architecture Search for Object Detection

https://github.com/MindSpore-paper-code-3/code7/tree/main/FaceAttribute

Deep Residual Learning for Image Recognition

https://github.com/MindSpore-paper-code-3/code7/tree/main/FaceDetection

Face Detection with End-to-End Integration of a ConvNet and a 3D Model

https://github.com/MindSpore-paper-code-3/code7/tree/main/erfnet

https://github.com/MindSpore-paper-code-3/code7/tree/main/fairmot

FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

https://github.com/MindSpore-paper-code-3/code7/tree/main/faster_rcnn_dcn

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

https://github.com/MindSpore-paper-code-3/code7/tree/main/fastscnn

Fast-SCNN: Fast Semantic Segmentation Network

https://github.com/MindSpore-paper-code-3/code7/tree/main/frustum-pointnet

Frustum PointNets for 3D Object Detection from RGB-D Data

https://github.com/MindSpore-paper-code-3/code7/tree/main/ghostnetv2

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

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