ARTEMIS framework enhances video polyp segmentation with agent-guided temporal mask evolution

Researchers have introduced ARTEMIS, a new framework designed to improve video polyp segmentation using imperfect supervision. This method leverages a vision-language agent to identify reliable temporal anchors from sparse annotations like points and scribbles, which are then propagated using SAM2 to refine masks across frames. ARTEMIS incorporates a temporal reliability-aware robust learning approach to assess mask quality and effectively train the segmentation model, outperforming existing methods on benchmark datasets. AI

IMPACT This research could lead to more accurate and efficient medical imaging analysis tools, particularly in endoscopy.

RANK_REASON The item is a research paper detailing a new method for video polyp segmentation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• ARTEMIS
• arXiv
• CatalyzeX
• CVC-ClinicDB-612
• DagsHub
• Gotit.pub
• Hugging Face
• SAM2
• ScienceCast
• SUN-SEG

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →