AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Looking in the Mirror: A Faithful Counterfactual Explanation Method for Interpreting Deep Image Classification Models

Townim Chowdhury, Vu Minh Hieu Phan, Kewen Liao, Nanyu Dong, Minh-Son To, Anton van den Hengel, Johan W. Verjans, Zhibin Liao

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 2 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 CAM-guided spatial prior (CSP) (ablation)Mirror-CFE SSC module · CelebA-HQvalidity (Val.): 0.78 -> 0.94Improved
add CAM-guided spatial prior (CSP) (ablation)Mirror-CFE SSC module · CelebA-HQFID: 40.12 -> 8.97Improved
add spatial pattern editor over plain skip connection (ablation)Mirror-CFE SSC module · CelebA-HQvalidity (Val.): 0.03 -> 0.94Improved
use alpha 0.2 instead of alpha 0 in triangulation loss (ablation)Mirror-CFE · F-MNIST (k=1)validity (Val.): 0.905 -> 0.949Improved
add triangulation loss (alpha 0.2) (ablation)Mirror-CFE · F-MNIST (k=1)denoised validity (D.Val): 0.921 -> 0.960Improved
add triangulation loss (alpha 0.2) (ablation)Mirror-CFE · F-MNIST (k=1)validity (Val.): 0.971 -> 0.949Hurt
change alpha among 0, 0.2, 0.4, 0.6 (ablation)Mirror-CFE · F-MNIST (k not 1)L1: 0.126 -> 0.127 -> 0.128 -> 0.116No clear effect
train multiclass instead of pairwise (ablation)Mirror-CFE · MNISTFID: 3.20 -> 6.94Hurt
train multiclass instead of pairwise (ablation)Mirror-CFE · F-MNISTL1: 0.25 -> 0.20Improved
move from 1st CFE to reflection point k=1Mirror-CFE · B-MNISTFID: 86.02 -> 132.93Hurt
move from 1st CFE to reflection point k=1Mirror-CFE · F-MNISTdenoised validity (D.Val): 0.99 -> 0.96Hurt
use Mirror-CFE instead of C3LTMirror-CFE (k=1) · MNISTdenoised validity (D.Val): 0.79 -> 0.99Improved

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