AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Tuning Medical Foundation Models for Inner Ear Temporal CT Analysis with Plug-and-play Domain Knowledge Aggregator

Weixun Wan, Xinyang Jiang, Zilong Wang, Bei Li, Cairong Zhao

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DKA with domain knowledge tokens to the foundation model instead of full fine-tuningMerlin · CIED outcome predictionF1 (%): 77.17 -> 92.49Improved
add DKA with domain knowledge tokens instead of full fine-tuningCT-FM · CIED six-class structural abnormality (micro)F1 (%): 22.88 -> 48.33Improved
add DKA instead of full fine-tuningMerlin · CIED six-class structural abnormality (micro)F1 (%): 80.14 -> 80.79No clear effect
add DKA instead of full fine-tuningSAM-Med3D · CIED binary structural abnormalityF1 (%): 50.97 -> 76.71Improved
use LoRA on SAM-Med3D instead of DKGTSAM-Med3D · CIED outcome predictionF1 (%): 58.16±30.37 vs DKGT 80.08±9.09Hurt
use adapter (655.23M parameters) on SAM-Med3D instead of DKGTSAM-Med3D · CIED binary structural abnormalityF1 (%): 35.57 vs DKGT 76.71Hurt
fuse domain knowledge features with 3DResNet by late fusion3DResNet · CIED binary structural abnormalityF1 (%): 50.46 -> 52.49Improved
add DKA module to SAM-Med3D (element-wise addition design) (ablation)SAM-Med3D · CIED outcome predictionF1 (%): 70.25 -> 80.08Improved
let image tokens query domain knowledge tokens instead of reversing the query direction (ablation)DKA on SAM-Med3D · CIED outcome predictionF1 (%): 76.04 -> 80.08Improved
combine learnable context tokens and domain tokens by element-wise addition instead of concatenation (ablation)DKA on SAM-Med3D · CIED outcome predictionF1 (%): 78.28 -> 80.08Improved
add domain knowledge from all three structures (IAM, cochlea, CNC) instead of none (ablation)DKGT on CT-FM · CIED outcome predictionF1 (%): 78.24 -> 82.55Improved
add domain knowledge from all three structures instead of none (ablation)DKGT on Merlin · CIED outcome predictionF1 (%): 91.35 -> 92.49Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy