MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation
Paper • 2602.20423 • Published • 3
Taha Koleilat
TahaKoleilat
AI & ML interests
Vision-Language Models, Domain Adaptation, Medical Image Analysis
Recent Activity
updated a dataset 3 days ago
TahaKoleilat/BiomedCoOp new activity about 1 month ago
TahaKoleilat/MedCLIPSeg:please new activity about 1 month ago
TahaKoleilat/MedCLIPSeg:Add pipeline_tag and improve model card metadataOrganizations
None yet
submitted a
paper to Daily Papers 2 months ago
authored a
paper 2 months ago
authored 6
papers 8 months ago
Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention
Paper • 2502.13693 • Published • 3
Singular Value Few-shot Adaptation of Vision-Language Models
Paper • 2509.03740 • Published • 3
MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation
Paper • 2409.19483 • Published
MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation
Paper • 2403.20253 • Published
TextSAM-EUS: Text Prompt Learning for SAM to Accurately Segment Pancreatic Tumor in Endoscopic Ultrasound
Paper • 2507.18082 • Published
GroundingDINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models
Paper • 2506.23903 • Published