How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Source free Single and Multi target Unsupervised Domain Adaptation
The main features of vcl-iisc/conmix are: Multi-Target Adaptation, Source Free Domain Adaptation.
Projects with overlapping indexed features include: prasannapulakurthi/spm — Shuffle PatchMix (SPM) for Source-Free Domain Adaptation (ICIP 2025); patch-shuffle augmentation + confidence-margin… prasannapulakurthi/foreground-background-augmentation — ReID + SFDA - Dual-Region Augmentation (Foreground Noise + Background Shuffle) for robust person re-identification… davidpengucf/sfdahpe — python == 3.6.8 - pytorch ==1.1.0 - torchvision == 0.3.0 - numpy, scipy, sklearn, PIL, argparse, tqdm. haifengxia/sfda. jxhuang0508/hcl — <Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data> in NIPS 2021. driptarc/decision — Unsupervised Multi-source Domain Adaptation Without Access to Source Data (CVPR '21 Oral).
Shuffle PatchMix (SPM) for Source-Free Domain Adaptation (ICIP 2025); patch-shuffle augmentation confidence-margin pseudo-labels. New SOTA on PACS (+7.3%), strong results on DomainNet-126 and VisDA-C.
ReID SFDA - Dual-Region Augmentation (Foreground Noise Background Shuffle) for robust person re-identification (ReID) and source-free domain adaptation (SFDA).
python == 3.6.8 - pytorch ==1.1.0 - torchvision == 0.3.0 - numpy, scipy, sklearn, PIL, argparse, tqdm
Unsupervised Multi-source Domain Adaptation Without Access to Source Data (CVPR '21 Oral)