AI Paper Atlas

Research map / Detection and segmentation / CNN features

ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging

Alessandro Fontanella, Antreas Antoniou, Wenwen Li, Joanna Wardlaw, Grant Mair, Emanuele Trucco, Amos Storkey

ICML 2023 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 4 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 saliency-attention modules (ACAT)baseline CNN · IST-3accuracy: 71.39% -> 72.55%Improved
add saliency-attention modules (ACAT)ResNet-50 baseline · MosMedaccuracy: 67.71% -> 70.84%Improved
use image-feature attention (SpAtt) instead of saliency attentionbaseline CNN · IST-3accuracy: 71.39% -> 70.96%No clear effect
replace CNN with vision transformerbaseline CNN · IST-3accuracy: 71.39% -> 57.87%Hurt
use gradient saliency maps instead of adversarial counterfactual maps (ablation)ACAT · IST-3accuracy: 72.55% -> 72.16%Hurt
use Grad-CAM saliency maps instead of ours (ablation)ACAT · IST-3accuracy: 72.55% -> 69.42%Hurt
also remove late attention layer (ablation)ACAT · MosMedaccuracy: 69.79% -> 68.75%Hurt
also remove middle attention layer (ablation)ACAT · MosMedaccuracy: 68.75% -> 68.23%Hurt
add random dropout (p=0.2) on image features instead of saliency attention (ablation)baseline · IST-3accuracy: 71.39% -> 68.71%Hurt
add random dropout (p=0.2) on image features instead of saliency attention (ablation)baseline · MosMedaccuracy: 67.71% -> 53.13%Hurt
progressive latent-space counterfactual saliency instead of latent shiftsaliency generation · IST-3 lesion locationhit rate S: 58.39% -> 65.05%Improved
use ACAT as classifier to generate counterfactual saliency mapssaliency generation · IST-3 lesion locationhit rate S: 65.05% -> 68.55%Improved

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