reqo.bsky.social @reqo.bsky.social · 03/04/2025This approach enables input-specific model construction without additional training and offers scalable, interpretable, and privacy-preserving adaptation. 000
reqo.bsky.social @reqo.bsky.social · 03/04/2025SemLA 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. 100
reqo.bsky.social @reqo.bsky.social · 03/04/2025We propose Semantic Library Adaptation (SemLA), a training-free method for test-time domain adaptation in open-vocabulary semantic segmentation. 100
reqo.bsky.social @reqo.bsky.social · 03/04/2025Our 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/...arxiv.orgSemantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic SegmentationOpen-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. Howeve... 111
Reposted by @reqo.bsky.socialDaniel Cremers @dcremers.bsky.social · 13/03/2025We 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 13612
Reposted by @reqo.bsky.socialKosta Derpanis @csprofkgd.bsky.social · 09/02/2025Please reshare this message widely! 013
