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.
Upcycling Models under Domain and Category Shift
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation
Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation
A Comprehensive Survey on Source-free Domain Adaptation
Semantic Image Segmentation: Two Decades of Research
In Search for a Generalizable Method for Source Free Domain Adaptation
When Source-Free Domain Adaptation Meets Learning with Noisy Labels
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation
Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track
Adversarial Alignment for Source Free Object Detection
Source-Free Domain Adaptation for Question Answering with Masked Self-training
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation
Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation
Anatomy-guided domain adaptation for 3D in-bed human pose estimation
ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
TTTFlow: Unsupervised Test-Time Training with Normalizing Flow
Variational Model Perturbation for Source-Free Domain Adaptation
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
Uncertainty-guided Source-free Domain Adaptation
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
Feed-Forward Latent Domain Adaptation
Source-Free Domain Adaptation for Real-world Image Dehazing
Balancing Discriminability and Transferability for Source-Free Domain Adaptation
Test-Time Adaptation for Visual Document Understanding
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
Active Source Free Domain Adaptation
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
Source-Free Domain Adaptation via Distribution Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.