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/clovaai/SATRN

On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention

https://github.com/cocofeat/tbrats

Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated Uncertainty

https://github.com/code-implementation1/Code4/tree/main/ibnnet

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

https://github.com/code-implementation1/Code6/tree/main/OSVOS

One-Shot Video Object Segmentation

https://github.com/code-implementation1/Code6/tree/main/PSPNet

Pyramid Scene Parsing Network

https://github.com/code-implementation1/Code6/tree/main/nnUNet

nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

https://github.com/code-implementation1/Code8/tree/main/SPPNet

SPPNet: A Single-Point Prompt Network for Nuclei Image Segmentation

https://github.com/code-implementation1/Code8/tree/main/Segformer

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

https://github.com/code-implementation1/Code8/tree/main/SinGAN

SinGAN-Seg: Synthetic training data generation for medical image segmentation

https://github.com/code-implementation1/Code9/tree/main/DeepLabV3P

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

https://github.com/code-implementation1/Code9/tree/main/MaskRCNN/maskrcnn_mobilenetv1

Mask R-CNN

https://github.com/code-implementation1/Code9/tree/main/Unet

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

https://github.com/code-implementation1/Code9/tree/main/VIT

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

https://github.com/cokowpublic/Nuclei-Segmentation

Mask R-CNN

https://github.com/collectionslab/Omniscribe

Mask R-CNN

https://github.com/collectionslab/annotations-computervision

Mask R-CNN

https://github.com/collectionslab/book-annotation-classification

Mask R-CNN

https://github.com/computational-cell-analytics/micro-sam

Segment Anything

https://github.com/computational-cell-analytics/peft-sam

Segment Anything

https://github.com/compvis/imagebart

Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions

https://github.com/condiff-dataset/ConDiff

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/cooparation/FCN_play

Fully Convolutional Networks for Semantic Segmentation

https://github.com/coperception/coperception

Who2com: Collaborative Perception via Learnable Handshake Communication

https://github.com/coradlut/bi-jros

Segment Anything

https://github.com/cosmic-cortex/pytorch-UNet

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/courao/ocr.pytorch

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/cplab/annolid

Annolid: Annotate, Segment, and Track Anything You Need

https://github.com/cpn/ShuffledVideoSorter

MobileNetV2: Inverted Residuals and Linear Bottlenecks

https://github.com/craig-m-k/W-Net

W-Net: A Deep Model for Fully Unsupervised Image Segmentation

https://github.com/crowdai/crowdai-mapping-challenge-mask-rcnn

Mask R-CNN

https://github.com/crs4/AtlantaNet

https://github.com/ctuning/ck-mlperf

MobileNetV2: Inverted Residuals and Linear Bottlenecks

https://github.com/cufctl/segmentation

AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation

https://github.com/cviviers/prob_3d_segmentation

Improving Aleatoric Uncertainty Quantification in Multi-Annotated Medical Image Segmentation with Normalizing Flows

https://github.com/cvlab-kaist/MUG-VOS

Multi-Granularity Video Object Segmentation

https://github.com/cvrl/opensourceirisrecognition

Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation

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