Papers with Code 아카이브

Source-Free Domain Adaptation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 7
보존된 평가 기록: 19

Source-Free Domain Adaptation (SFDA) is a domain adaptation method in machine learning and computer vision where the goal is to adapt a pre-trained model to a new, target domain without access to the source domain data. This approach is advantageous in scenarios where sharing the source data is impractical due to privacy concerns, data size, or proprietary restrictions

코드

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

https://github.com/hilab-git/upl-sfda

공식 코드

UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation

https://github.com/hyeonwoocho7/cng-sfda

공식 코드

CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation

https://github.com/ismailnejjar/RRDA

공식 코드

Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework

https://github.com/ispc-lab/bmd

공식 코드

BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation

https://github.com/ispc-lab/glc

공식 코드

Upcycling Models under Domain and Category Shift

https://github.com/ispc-lab/glc-plus

공식 코드

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

https://github.com/jinghuaman/aif-sfda

공식 코드

AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation

https://github.com/jingwang18/silan

공식 코드

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

https://github.com/jo-wang/cal-sfda

공식 코드

Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error

https://github.com/jonas-lippl/fact

공식 코드

FACT: Federated Adversarial Cross Training

https://github.com/kinredon/umt

공식 코드

Unbiased Mean Teacher for Cross-domain Object Detection

https://github.com/lbktrinh/DRU

공식 코드

Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection

https://github.com/lingrayy/plpb

공식 코드

Robust Source-Free Domain Adaptation for Fundus Image Segmentation

https://github.com/lloongx/sfda-cbmt

공식 코드

Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher

https://github.com/luo-junyu/gala

공식 코드

GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation

https://github.com/maohaos2/MSFDA

공식 코드

On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation

https://github.com/mathilde-b/SFDA

공식 코드

Source-Free Domain Adaptation for Image Segmentation

https://github.com/mattialitrico/guiding-pseudo-labels-with-uncertainty-estimation-for-source-free-unsupervised-domain-adaptation

공식 코드

Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation

https://github.com/mattialitrico/guiding-pseudo-labels-with-uncertainty-estimation-for-test-time-adaptation

공식 코드

Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation

https://github.com/maxwellyin/mdaqa

공식 코드

Source-Free Domain Adaptation for Question Answering with Masked Self-training

https://github.com/michiganleon/reclip_wacv

공식 코드

ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation

https://github.com/mmjing/variational_model_perturbation

공식 코드

Variational Model Perturbation for Source-Free Domain Adaptation

https://github.com/mohamedr002/mapu_sfda_ts

공식 코드

Source-Free Domain Adaptation with Temporal Imputation for Time Series Data

https://github.com/multimodallearning/da-3dhpe-anatomy

공식 코드

Anatomy-guided domain adaptation for 3D in-bed human pose estimation

https://github.com/multimodallearning/dg-tta

공식 코드

DG-TTA: Out-of-domain Medical Image Segmentation through Augmentation and Descriptor-driven Domain Generalization and Test-Time Adaptation

https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation

공식 코드

C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation

https://github.com/nkdinsdale/sfharmony

공식 코드

SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis

https://github.com/osmanberke/sfda-ssvep-bci

공식 코드

Source-Free Domain Adaptation for SSVEP-based Brain-Computer Interfaces

https://github.com/paolomandica/HALO

공식 코드

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

https://github.com/roysubhankar/uncertainty-sfda

공식 코드

Uncertainty-guided Source-free Domain Adaptation

https://github.com/se111/side

공식 코드

SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation

https://github.com/shallowdream204/SODA-SR

공식 코드

Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer

https://github.com/shaoyuanlo/stpl

공식 코드

Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation

https://github.com/shinyflight/sfda2

공식 코드

SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation

https://github.com/shishuaihu/prosfda

공식 코드

ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation

https://github.com/ssi-research/dcpl_sfda

공식 코드

De-Confusing Pseudo-Labels in Source-Free Domain Adaptation

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