MedCore: Boundary-Preserving Medical Core Pruning for MedSAM
cs.CV, cs.LG
Submitted: 2026-05-13
Updated: 2026-10-29
Comments: 3 figures, 21 pages
Code: https://github.com/cenweizhang/MedCore
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Segment Anything
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Polyp-SAM: Transfer SAM for Polyp Segmentation
- I-MedSAM: Implicit Medical Image Segmentation with Segment Anything
- MedSAM2: Segment Anything in 3D Medical Images and Videos
- Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
- Revisiting Random Channel Pruning for Neural Network Compression
- Learning both Weights and Connections for Efficient Neural Networks
- Are Sixteen Heads Really Better than One?
- Faster gaze prediction with dense networks and Fisher pruning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs