This approach enables input-specific model construction without additional training and offers scalable, interpretable, and privacy-preserving adaptation.

SemLA dynamically computes a weighted average over LoRA-based adapters from the most relevant source domains, where weights are determined by the semantic similarity between each source domain and the target input, as measured in the CLIP embedding space.

We propose Semantic Library Adaptation (SemLA), a training-free method for test-time domain adaptation in open-vocabulary semantic segmentation.

Our paper, ”Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation”, has been accepted to #CVPR 2025.

📄 Paper: arxiv.org/abs/2503.21780
🧪 Code: github.com/rezaqorbani/...

We are thrilled to have 12 papers accepted to #CVPR2025. Thanks to all our students and collaborators for this great achievement!
For more details check out cvg.cit.tum.de

This is great, thank you for sharing!

Please reshare this message widely!