Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention

cs.CV, cs.LG

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: Accepted at the 5th Workshop on Applications of Medical AI (AMAI), MICCAI 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
• BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models