Curated resources for Source‑Free Domain Adaptation (SFDA): methods that adapt using only a trained source model (no source data). Includes papers, code, datasets, benchmarks, and tutorials.
- AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation (AAAI 2025) [arxiv] [code]
- Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment (CVPR 2025) [paper] [pdf]
- Effective dual-region augmentation for reduced reliance on large amounts of labeled data (2025) [paper] [arxiv] [code]
- ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation (arXiv 2025) [arxiv]
- Label Calibration in Source Free Domain Adaptation (WACV 2025) [paper] [arxiv]
- Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation (CVPR 2025) [paper]
- Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing (CVPR 2025) [paper] [arxiv]
- PointSFDA: Source-free Domain Adaptation for Point Cloud Completion (arXiv 2025) [arxiv] [code]
- ProSFDA: Source-free Domain Adaptation Using Prompt Learning for Medical Image Segmentation (Pattern Recognition 2025) [paper] [code]
- Proxy Denoising for Source-Free Domain Adaptation (ICLR 2025) [paper] [arxiv]
- Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control (ICLR 2025) [paper] [code]
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025) [paper]
- Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation (ICIP 2025) [paper] [arxiv] [code]
- Source-free Video Domain Adaptation by Learning from Noisy Labels (Pattern Recognition 2025) [paper] [code]
- Unraveling the Mysteries of Label Noise in Source-Free Domain Adaptation: Theory and Practice (TPAMI 2025) [paper] [code]
- VP-SFDA: Visual Prompt Source-Free Domain Adaptation for Cross-Modal Medical Image Segmentation (Health Data Science 2025) [paper]
- A Comprehensive Survey on Source-Free Domain Adaptation (TPAMI 2024) [paper] [arxiv]
- Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation (WACV 2024) [paper]
- De-Confusing Pseudo-Labels in Source-Free Domain Adaptation (ECCV 2024) [paper] [arxiv] [code]
- EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition (CVPR 2024) [paper] [code]
- GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation (TPAMI 2024) [paper]
- Hierarchical Unsupervised Relation Distillation for Source-Free Domain Adaptation (ECCV 2024) [paper]
- Neighborhood-Aware Mutual Information Maximization for SFDA (TMM 2024) [paper]
- ReCLIP: Refine Contrastive Language Image Pre-Training with SFDA (WACV 2024) [paper] [arxiv] [code]
- Robust Nearest Neighbors for Source-Free Domain Adaptation under Class Distribution Shift (ECCV 2024) [paper] [code]
- Robust Source-Free Domain Adaptation for Fundus Image Segmentation (WACV 2024) [paper] [code]
- SepRep-Net: Multi-source Free Domain Adaptation via Model Separation and Reparameterization (arXiv 2024) [paper]
- SF(DA)²: Source-free Domain Adaptation Through the Lens of Data Augmentation (ICLR 2024) [paper] [arxiv] [code]
- SFDA for RGB-D Semantic Segmentation with Vision Transformers (arXiv 2024) [paper]
- SFDA with Diffusion-Guided Source Data Generation (arXiv 2024) [paper]
- SFDA with Frozen Multimodal Foundation Model (CVPR 2024) [paper] [arxiv]
- Simplifying Source-Free Domain Adaptation for Object Detection (ECCV 2024) [paper] [arxiv] [code]
- Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation (CVPR 2024) [paper] [arxiv] [code]
- Towards Stable and Robust Source-free Unsupervised 3D Semantic Segmentation (ECCV 2024) [paper]
- Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer (CVPR 2024) [paper] [arxiv] [code]
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024) [paper] [code]
- Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation (CVPR 2024) [paper] [code]
- Visually Source-Free Domain Adaptation via Adversarial Style Matching (TIP 2024) [paper]
- Office-31
- Office-Home
- VISDA-C
- DomainNet (cleaned)
- PACS
- ImageNet-A
- ImageNet-R
- ImageNet-V2
- ImageNet-Sketch
- Add libraries and tooling here.
- Add tutorials and talks here.
Please read CONTRIBUTING.md. Use this entry format:
- Title (Venue/Year) [[paper](https://example.com/paper)] [[code](https://example.com/code)] [[project](https://example.com/site)]
Sorting policy:
- Sort entries alphabetically by title within each section.