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/fiabdu/Commonly-Interesting-Images

Learning Transferable Visual Models From Natural Language Supervision

https://github.com/fidler-lab/social-driving

nuScenes: A multimodal dataset for autonomous driving

https://github.com/filaPro/visda2019

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/filipbasara0/simple-clip

Learning Transferable Visual Models From Natural Language Supervision

https://github.com/filipmu/Kaggle-APTOS-2019-Blindness

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/filippogiruzzi/semantic_segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/finepix/small_object_augmentation

Augmentation for small object detection

https://github.com/firja10/darknet-2

YOLOv3: An Incremental Improvement

https://github.com/fizyr/keras-retinanet

Focal Loss for Dense Object Detection

https://github.com/flaudem/ProjetDeepLearnig_IAS

Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high resolution RGB labelled images to develop and benchmark wheat head detection methods

https://github.com/flj19951219/mamba_dose

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

https://github.com/floatingstarZ/loc_cls_exp

MMDetection: Open MMLab Detection Toolbox and Benchmark

https://github.com/flyfly666/mmdetection2.18.1

Instances as Queries

https://github.com/flyingTan/QuantMmdetection

MMDetection: Open MMLab Detection Toolbox and Benchmark

https://github.com/flytocc/ConvNeXt-paddle

A ConvNet for the 2020s

https://github.com/flytocc/CycleMLP-paddle

CycleMLP: A MLP-like Architecture for Dense Prediction

https://github.com/flytocc/PaddleClas

PP-LCNet: A Lightweight CPU Convolutional Neural Network

https://github.com/flytocc/PeleeNet-paddle

Pelee: A Real-Time Object Detection System on Mobile Devices

https://github.com/flytocc/mae-paddle

Masked Autoencoders Are Scalable Vision Learners

https://github.com/fnando1995/INTEL_Project

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

https://github.com/fofore/yolov3-pyroch

YOLOv3: An Incremental Improvement

https://github.com/fogfog2/packnet

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

https://github.com/forcefulowl/image_classification

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

https://github.com/fountain-y/ranksortloss

Rank & Sort Loss for Object Detection and Instance Segmentation

https://github.com/fourmi1995/IronExperiment-DCN

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

https://github.com/francisengelmann/3D-MPA

3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation

https://github.com/frank-roesler/Image_Segmentation

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

https://github.com/frank-xwang/TBC-TiedBlockConvolution

Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

https://github.com/frank-xwang/towards-universal-object-detection

Towards Universal Object Detection by Domain Attention

https://github.com/franknb/Self-attention-DCGAN

Non-local Neural Networks

https://github.com/fredotran/traffic-sign-detector-yolov4

YOLOv3: An Incremental Improvement

https://github.com/fredotran/traffic-signs-detection

YOLOv3: An Incremental Improvement

https://github.com/fredotran/yolov3-opencvdnn

YOLOv3: An Incremental Improvement

https://github.com/freeniliang/caffe-fastercnn-rfcn

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

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

SSD: Single Shot MultiBox Detector

https://github.com/fregu856/deeplabv3

Rethinking Atrous Convolution for Semantic Image Segmentation

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