Papers with Code 아카이브

Semantic Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

29

평가표

150

보존된 평가 기록

1,918

코드

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

https://github.com/nowsyn/instmatt

공식 코드

Human Instance Matting via Mutual Guidance and Multi-Instance Refinement

https://github.com/nsavinov/semantic3dnet

공식 코드

Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark

https://github.com/nspunn1993/bt-unet

공식 코드

BT-Unet: A self-supervised learning framework for biomedical image segmentation using Barlow Twins with U-Net models

https://github.com/nstucki/betti-matching

공식 코드

Topologically faithful image segmentation via induced matching of persistence barcodes

https://github.com/ntnu-smallsat-lab/s_l_c_segm_hyp_img

공식 코드

Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning

https://github.com/nubagcilab/diffboost

공식 코드

DiffBoost: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model

https://github.com/nubagcilab/pediatric-brain-tumor-segmentation-model

공식 코드

A New Logic For Pediatric Brain Tumor Segmentation

https://github.com/nubot-nudt/doss

공식 코드

A Novel Decomposed Feature-Oriented Framework for Open-Set Semantic Segmentation on LiDAR Data

https://github.com/nubot-nudt/elc-ois

공식 코드

ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Data

https://github.com/nubot-nudt/insmos

공식 코드

InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data

https://github.com/nubot-nudt/segnet4d

공식 코드

SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud

https://github.com/numisveinsson/SeqSeg

공식 코드

SeqSeg: Learning Local Segments for Automatic Vascular Model Construction

https://github.com/nus-hpc-ai-lab/dynamic-tuning

공식 코드

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

https://github.com/nus-hpc-ai-lab/infobatch

공식 코드

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

https://github.com/nus-tim/dems

공식 코드

Segmenting Medical Images with Limited Data

https://github.com/nust-machine-intelligence-laboratory/hcpn

공식 코드

Co-attention Propagation Network for Zero-Shot Video Object Segmentation

https://github.com/nust-machine-intelligence-laboratory/hgpu

공식 코드

Hierarchical Graph Pattern Understanding for Zero-Shot VOS

https://github.com/nust-machine-intelligence-laboratory/hpan

공식 코드

Holistic Prototype Attention Network for Few-Shot VOS

https://github.com/nust-machine-intelligence-laboratory/hvc

공식 코드

Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation

https://github.com/nust-machine-intelligence-laboratory/i2crc

공식 코드

Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation

https://github.com/nust-machine-intelligence-laboratory/ktse

공식 코드

Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation

https://github.com/nust-machine-intelligence-laboratory/mccl

공식 코드

Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning

https://github.com/nust-machine-intelligence-laboratory/mdba

공식 코드

Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation

https://github.com/nust-machine-intelligence-laboratory/ssc

공식 코드

Spatial Structure Constraints for Weakly Supervised Semantic Segmentation

https://github.com/nust-machine-intelligence-laboratory/torchsemiseg2

공식 코드

Semi-Supervised Semantic Segmentation With Region Relevance

https://github.com/nust-machine-intelligence-laboratory/videomac

공식 코드

VideoMAC: Video Masked Autoencoders Meet ConvNets

https://github.com/nv-dvl/segment-anything-lidar

공식 코드

Better Call SAL: Towards Learning to Segment Anything in Lidar

https://github.com/nv-nguyen/cnos

공식 코드

CNOS: A Strong Baseline for CAD-based Novel Object Segmentation

https://github.com/nv-tlabs/datasetGAN_release

공식 코드

DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort

https://github.com/nv-tlabs/lift-splat-shoot

공식 코드

Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D

https://github.com/nvakhoa/superclass-fsis

공식 코드

Instance-level Few-shot Learning with Class Hierarchy Mining

https://github.com/nveldt/SparseCardDSFM

공식 코드

Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components

https://github.com/nvidia/torch-harmonics

공식 코드

Attention on the Sphere

https://github.com/nvlabs/3dgm

공식 코드

Memorize What Matters: Emergent Scene Decomposition from Multitraverse

https://github.com/nvlabs/fan

공식 코드

Understanding The Robustness in Vision Transformers

https://github.com/nvlabs/freesolo

공식 코드

FreeSOLO: Learning to Segment Objects without Annotations

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