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/haochenheheda/SwiftNet

공식 코드

SwiftNet: Real-time Video Object Segmentation

https://github.com/haochenz11/iref-vla

공식 코드

IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes

https://github.com/haoli12345/cats

공식 코드

CATS v2: Hybrid encoders for robust medical segmentation

https://github.com/haoningwu3639/MRGen

공식 코드

MRGen: Diffusion-based Controllable Data Engine for MRI Segmentation towards Unannotated Modalities

https://github.com/haoshao-nku/medical_seg

공식 코드

MCANet: Medical Image Segmentation with Multi-Scale Cross-Axis Attention

https://github.com/haowang420/boemd-net

공식 코드

Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural Networks

https://github.com/happy-hsy/motionmae

공식 코드

Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

https://github.com/haranrk/DigiPathAI

공식 코드

A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysis

https://github.com/harboryuan/polyphonicformer

공식 코드

PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

https://github.com/hardyho/ultrametric_feature_fields

공식 코드

View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields

https://github.com/harkiratbehl/MetaVOS

공식 코드

Meta Learning Deep Visual Words for Fast Video Object Segmentation

https://github.com/harrytea/adaptvision

공식 코드

AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding

https://github.com/harrytea/detect-anyshadow

공식 코드

Detect Any Shadow: Segment Anything for Video Shadow Detection

https://github.com/harrytea/root

공식 코드

ROOT: VLM based System for Indoor Scene Understanding and Beyond

https://github.com/harvard-ophthalmology-ai-lab/fairdomain

공식 코드

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

https://github.com/harvard-ophthalmology-ai-lab/fairseg

공식 코드

FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling

https://github.com/hashmatshadab/apr

공식 코드

Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations

https://github.com/hasibzunair/rsud20k

공식 코드

RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving

https://github.com/hasibzunair/sharp-unets

공식 코드

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

https://github.com/havrylovv/isegprobe

공식 코드

Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation

https://github.com/hbyecoding/u-rwkv

공식 코드

U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV

https://github.com/hci-unihd/pytorch-LearnedRandomWalker

공식 코드

End-to-End Learned Random Walker for Seeded Image Segmentation

https://github.com/hcplab-sysu/stket

공식 코드

Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation

https://github.com/healthml/active-segmentation

공식 코드

Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation

https://github.com/healthx-lab/deepsegthoracic

공식 코드

Architecture Analysis and Benchmarking of 3D U-shaped Deep Learning Models for Thoracic Anatomical Segmentation

https://github.com/healthx-lab/medclip-samv2

공식 코드

MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation

https://github.com/hebeifast/eventlowlightvos

공식 코드

Event-assisted Low-Light Video Object Segmentation

https://github.com/hejrati/cdal

공식 코드

Conditional diffusion model with spatial attention and latent embedding for medical image segmentation

https://github.com/helblazer811/ConceptAttention

공식 코드

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

https://github.com/helen1c/mc-panda

공식 코드

MC-PanDA: Mask Confidence for Panoptic Domain Adaptation

https://github.com/hendrycks/robustness

공식 코드

Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning

https://github.com/heng-hw/spacap3d

공식 코드

Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

https://github.com/heng-yuwen/dynamic-backward-attention-transformer

공식 코드

DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches

https://github.com/heng-yuwen/matspectnet

공식 코드

MatSpectNet: Material Segmentation Network with Domain-Aware and Physically-Constrained Hyperspectral Reconstruction

https://github.com/heng14/gpu-net

공식 코드

GPU-Net: Lightweight U-Net with more diverse features

https://github.com/hengcai-nju/3d2dct

공식 코드

3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks

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