Papers with Code 아카이브

2D Semantic Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

17

평가표

11

보존된 평가 기록

42

코드

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

https://github.com/jamiljami/Unet

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jamycheung/360BEV

Joint 2D-3D-Semantic Data for Indoor Scene Understanding

https://github.com/janelia-flyem/NeuroProof

Focused Proofreading: Efficiently Extracting Connectomes from Segmented EM Images

https://github.com/janisgp/Sampling-free-Epistemic-Uncertainty

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

https://github.com/jasjeetIM/Mask-RCNN

Mask R-CNN

https://github.com/javiergarciamolina/selfie-background-removal

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jbardelli/Petrographic-Image-Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

https://github.com/jdfxzzy/pean

Text Image Inpainting via Global Structure-Guided Diffusion Models

https://github.com/jeasung-pf/MORAN_v2

A Multi-Object Rectified Attention Network for Scene Text Recognition

https://github.com/jeasung-pf/see

SEE: Towards Semi-Supervised End-to-End Scene Text Recognition

https://github.com/jellevankerk/Team-Challenge

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jercas/TextBoxes_plusplus_tf

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

https://github.com/jerichooconnell/tf_unet

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jetpacapp/DeepBeliefSDK

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

https://github.com/jeya-maria-jose/Overcomplete-Deep-Subspace-Clustering

KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations

https://github.com/jfzhang95/pytorch-deeplab-xception

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

https://github.com/jhihan/rsna_pneumonia_detection

Mask R-CNN

https://github.com/jiajunhua/facebookresearch-Detectron

Mask R-CNN

https://github.com/jiandai/mlTst

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jiangxiluning/FOTS.PyTorch

FOTS: Fast Oriented Text Spotting with a Unified Network

https://github.com/jianing-sun/Mask-YOLO

Mask R-CNN

https://github.com/jianpengz/ConResNet

Inter-slice Context Residual Learning for 3D Medical Image Segmentation

https://github.com/jianpengz/DoDNet

DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets

https://github.com/jiayan97/linknet-pytorch

LinkNet: Relational Embedding for Scene Graph

https://github.com/jiehu1996/deformablemamba

Joint 2D-3D-Semantic Data for Indoor Scene Understanding

https://github.com/jihaoxuanye/MetaPRD

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

https://github.com/jimgoo/caffe-oxford102

CNN Features off-the-shelf: an Astounding Baseline for Recognition

https://github.com/jinbac/PlantNet

MobileNetV2: Inverted Residuals and Linear Bottlenecks

https://github.com/jingsenzhu/i2-sdf

I$^2$-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

https://github.com/jinyangyuan/genesis

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

https://github.com/jiportilla/edge-max-object-detector

Microsoft COCO: Common Objects in Context

https://github.com/jishavm/TextStyleTransfer

Style Transfer from Non-Parallel Text by Cross-Alignment

https://github.com/jiwei0921/MVSS-Baseline

https://github.com/jiye-ML/unet_pytorch

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/jizongFox/deep-clustering-toolbox

Deep Co-Training for Semi-Supervised Image Segmentation

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