AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Learn-Explain-Reinforce: Counterfactual Reasoning and its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model

Kwanseok Oh, Jee Seok Yoon, Heung‐Il Suk

TPAMI 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Abstract visual reasoning benchmarks · 52 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
fine-tune backbone with counterfactual-map augmented imagesResNet18 · ADNI CN vs MCI vs ADaccuracy: 0.5802 -> 0.5883Improved
fine-tune backbone with counterfactual-map augmented imagesResNet18 · ADNI CN vs ADaccuracy: 0.8898 -> 0.9231Improved
add XGA guided by counterfactual maps instead of augmentation (ablation)ResNet18 · ADNI CN vs MCI vs ADaccuracy: 0.5883 -> 0.6715Improved
add XGA guided by counterfactual maps instead of augmentation (ablation)ResNet18 · ADNI CN vs ADaccuracy: 0.9231 -> 0.9489Improved
add XGA guided by counterfactual mapsResNet18 · ADNI sMCI vs pMCIaccuracy: 0.6946 -> 0.7703Improved
add XGA guided by counterfactual mapsResNet18 · ADNI CN vs MCI vs ADmAUC: 0.7501 -> 0.8123Improved
add second iteration of explanation-reinforcement learning (ablation)LEAR ResNet18 · ADNI CN vs MCI vs ADaccuracy: 0.6347 -> 0.6715Improved
add third iteration of explanation-reinforcement learning (ablation)LEAR ResNet18 · ADNI CN vs MCI vs ADaccuracy: 0.6715 -> 0.6715No clear effect
add third iteration of explanation-reinforcement learning (ablation)LEAR ResNet18 · ADNI CN vs ADaccuracy: 0.9515 -> 0.9489Hurt
add second iteration (ablation)LEAR ResNet18 · ADNI MCI vs ADaccuracy: 0.8396 -> 0.8716Improved
add explanation-guided attention to the diagnostic model, comparing to VA-GAN mapsCMG · ADNI CN<->AD NCC(+)NCC: 0.317 -> 0.366Improved
use CMG counterfactual maps instead of Grad-CAMexplanation method · ADNI CN<->AD NCC(+)NCC: 0.227 -> 0.366Improved

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