Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning

Documenti analoghi

• BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models
  di: Koleilat, Taha, et al.
  Pubblicazione: (2024)
• CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values
  di: Koleilat, Taha, et al.
  Pubblicazione: (2025)
• MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation
  di: Koleilat, Taha, et al.
  Pubblicazione: (2026)
• MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation
  di: Koleilat, Taha, et al.
  Pubblicazione: (2024)
• Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models
  di: Rasaee, Hamza, et al.
  Pubblicazione: (2025)