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/Albert0147/AaD_SFDA

공식 코드

Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation

https://github.com/Albert0147/BAIT_SFUDA

공식 코드

Casting a BAIT for Offline and Online Source-free Domain Adaptation

https://github.com/Albert0147/G-SFDA

공식 코드

Generalized Source-free Domain Adaptation

https://github.com/AlexisGuichemerreCode/survey_hist_wsol_sfda

공식 코드

Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology

https://github.com/BiQiWHU/CMFormer

공식 코드

Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation

https://github.com/CuriousAI/mean-teacher

공식 코드

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

https://github.com/DequanWang/tent

공식 코드

Tent: Fully Test-time Adaptation by Entropy Minimization

https://github.com/Dong-Jie-Chen/RCL

공식 코드

Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum Learning

https://github.com/LTTM/HyperFLAW

공식 코드

When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather

https://github.com/Lans1ng/SFOD-RS

공식 코드

CLIP-Guided Source-Free Object Detection in Aerial Images

https://github.com/MasoumehSharafi/DSFDA-for-Pain-Assessment

공식 코드

Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data

https://github.com/PrasannaPulakurthi/Foreground-Background-Augmentation

공식 코드

Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data

https://github.com/PrasannaPulakurthi/SPM

공식 코드

Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation

https://github.com/RenzKa/sign-segmentation

공식 코드

Sign Segmentation with Changepoint-Modulated Pseudo-Labelling

https://github.com/SCUT-AILab/CPGA

공식 코드

Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation

https://github.com/Tajamul21/Grounded_Teacher

공식 코드

Context Aware Grounded Teacher for Source Free Object Detection

https://github.com/YXSong000/UAD

공식 코드

Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation

https://github.com/YYinn/SFDA-DDFP

공식 코드

DDFP: Data-dependent Frequency Prompt for Source Free Domain Adaptation of Medical Image Segmentation

https://github.com/albert0147/sfda_neighbors

공식 코드

Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation

https://github.com/altndrr/clup

공식 코드

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition

https://github.com/bdlab405/sdalr

공식 코드

Source-free domain adaptation based on label reliability for cross-domain bearing fault diagnosis

https://github.com/brdav/cma

공식 코드

Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation

https://github.com/chrisantuseze/active-self-pretraining

공식 코드

A3: Active Adversarial Alignment for Source-Free Domain Adaptation

https://github.com/cianeastwood/bufr

공식 코드

Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration

https://github.com/cscyqj/miccai23-protocontra-sfda

공식 코드

Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning

https://github.com/daintlab/fewshot-sfda

공식 코드

Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation

https://github.com/duojun-huang/diana-cvpr2023

공식 코드

Divide and Adapt: Active Domain Adaptation via Customized Learning

https://github.com/encounter1997/SFA

공식 코드

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

https://github.com/epfl-imos/simple-sfod

공식 코드

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights

https://github.com/erosinho13/ladd

공식 코드

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

https://github.com/fenghz/cosda

공식 코드

CoSDA: Continual Source-Free Domain Adaptation

https://github.com/guoweiyu/spgesture

공식 코드

SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network

https://github.com/gustavovargashakim/tttflow

공식 코드

TTTFlow: Unsupervised Test-Time Training with Normalizing Flow

https://github.com/gxinuu/pcsr

공식 코드

Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation

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

공식 코드

SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation

https://github.com/hilab-git/ugtst

공식 코드

An Uncertainty-guided Tiered Self-training Framework for Active Source-free Domain Adaptation in Prostate Segmentation

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