Papers with Code 아카이브
Source-Free Domain Adaptation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation
Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
Test-time Batch Statistics Calibration for Covariate Shift
Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
Source-Free Domain Adaptation for Image Segmentation
Generalized Source-free Domain Adaptation
AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation
Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation
A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
Transformer-Based Source-Free Domain Adaptation
Sign Segmentation with Changepoint-Modulated Pseudo-Labelling
Source-Free Domain Adaptation for Semantic Segmentation
Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments
Casting a BAIT for Offline and Online Source-free Domain Adaptation
Source Free Domain Adaptation with Image Translation
Tent: Fully Test-time Adaptation by Entropy Minimization
Universal Source-Free Domain Adaptation
Unbiased Mean Teacher for Cross-domain Object Detection
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.