2 papers
cs.CV2026
CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation
Shayan Jalilian, Abdul Bais
Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. E…
cs.CV2025
SAM-PTx: Text-Guided Fine-Tuning of SAM with Parameter-Efficient, Parallel-Text Adapters
Shayan Jalilian, Abdul Bais
The Segment Anything Model (SAM) has demonstrated impressive generalization in prompt-based segmentation. Yet, the potential of semantic text prompts remains underexplored compared…