Counterfactual Image Generation

Follow this topic Ask about this topic

Latest papers

18 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

CLEAR: Cooperative Latent Flow for Visual Counterfactual Explanations with Accurate Region Preservation
Oct 16, 2026Yan Zeng, Changlu Guo, Oskar Kristoffersen +3Counterfactual Explanations Counterfactual Image Generation
Technical University of Denmark
Causal Spatio-Temporal Neural Distance Fields for Counterfactual Cardiac Anatomy
Oct 15, 2026Mathias Lowes, Kurt Butler, Kristine Aavild Sørensen +4Counterfactual Image Generation Causal Counterfactual Generation
DTU Compute, Technical University of Denmark, Kongens Lyngby, Denmark · Causality in Healthcare AI Hub (CHAI), UK · School of Engineering, University of Edinburgh, Edinburgh, UK +2
Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model
Sep 29, 2026Van Bach Nguyen, Jörg Schlötterer, Christin SeiferVision-Language Models VLM Interpretability
Marburg University, Germany
Generating Chest X-Ray Counterfactuals by Specialising Foundation Image Models
Sep 21, 2026Xiaodan Xing, Rajat R. Rasal, Julia A. Meister +3Medical Imaging Foundation Models Causal Counterfactual Generation
GSK · Imperial College London
MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation
Sep 14, 2026Yan Zeng, Changlu Guo, Anders Nymark Christensen +2Counterfactual Explanations Latent Diffusion Models
Department of Applied Mathematics and Computer Science, Technical University of Denmark
To do( $x$ ) or not to do( $x$ ): Medical Image Counterfactuals for Dataset Augmentation
Sep 12, 2026Yasin Ibrahim, Robin J. Evans, Konstantinos KamnitsasFairness in Medical Image Classification Counterfactual Data Augmentation
Department of Engineering Science, University of Oxford · Department of Statistics, University of Oxford
Generating Medical Image Counterfactuals using Causal Explanations
Sep 2, 2026David A. Kelly, Tom Yaacov, Nathan Blake +2Counterfactual Image Generation Counterfactual Explanations
King’s College London · University College London
When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images
Aug 24, 2026Andrea Posada, Wenke Karbole, Bach Ngoc Doan +9Counterfactual Image Generation Identity-Preserving Image Generation
Technical University of Munich and TUM University Hospital, Germany · Munich Center of Machine Learning (MCML), Munich, Germany · Munich Data Science Institute (MDSI), Munich, Germany +4
Can We Perform Online RL for Image Editing without Editing Rewards?
Aug 24, 2026Qichao Ma, Jikang Cheng, Ling Liang +3Counterfactual Image Generation RL for Image Editing
Peking University
Counterfactual Contrastive Analysis
Aug 19, 2026Yunlong He, Pietro GoriCounterfactual Explanations Image Generation
LTCI, Télécom Paris, Institut Polytechnique de Paris, France
FiRe: Fixed-Noise Refinement for Visual Counterfactual Explanations
Aug 9, 2026Yan Zeng, Changlu Guo, Oskar Kristoffersen +3Counterfactual Explanations Diffusion Guidance
Department of Applied Mathematics and Computer Science, Technical University of Denmark
Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
Jun 23, 2026Jiayi Lei, Yuandong Pu, Xingyu Han +8Causal Counterfactual Generation T2I Generation
Shanghai Jiao Tong University · Shanghai AI Laboratory · The Chinese University of Hong Kong
Leveraging Foundation Models for Causal Generative Modeling
May 22, 2026Aneesh Komanduri, Xintao WuCausal Counterfactual Generation Image Generation
University of Arkansas Fayetteville, Arkansas, USA
From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder
May 21, 2026Yilin Zhang, Nicholas C. Harvey, Nicholas R. Fuggle +1Medical Imaging Image Generation
School of Electronics and Computer Science University of Southampton Southampton, UK · MRC Lifecourse Epidemiology Centre University of Southampton, Southampton General Hospital Southampton, UK
Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution
May 6, 2026Shakeeb MurtazaFeature Attribution Counterfactual Explanations
COMSATS University Islamabad
Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis
Mar 22, 2026Tian Xia, Matthew Sinclair, Andreas Schuh +8Counterfactual Image Generation Image Generation
Department of Computing, Imperial College London, UK · HeartFlow, Inc., Mountain View, CA, USA
PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
Mar 7, 2026Trong-Thang Pham, Loc Nguyen, Anh Nguyen +2Counterfactual Image Generation Medical Image Synthesis
University of Arkansas, Fayetteville AR, USA · University of Liverpool, Liverpool, UK · University of Houston, Houston TX, USA
MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations
Feb 21, 2026Changlu Guo, Anders Nymark Christensen, Anders Bjorholm Dahl +1Counterfactual Image Generation Counterfactual Explanations
Technical University of Denmark, Denmark

Oct 16, 2026J/K move · Enter open · S save

CLEAR: Cooperative Latent Flow for Visual Counterfactual Explanations with Accurate Region Preservation

Yan Zeng, Changlu Guo, Oskar Kristoffersen, Anders Nymark Christensen+2

Technical University of Denmark

Counterfactual Explanations Counterfactual Image Generation Explainable Image Classification

Open paper AskPDF arXiv

Visual counterfactual explanations (VCEs) should alter a classifier's prediction while remaining realistic and preserving decision-irrelevant content. Image-space methods provide high-quality counterfactuals but are computationally costly, whereas latent-space methods are more efficient but often less faithful. We identify two sources responsible for this gap. First, latent generation recovers a natural sample from a perturbed representation, whereas classifier guidance pushes it toward a target class, so their update directions may oppose. Second, VAE reconstruction can alter regions that should remain unchanged. We introduce CLEAR, a latent Flow Matching framework for VCEs. CLEAR uses Flow Matching's explicit instantaneous velocity as a reference for the generative direction to decompose classifier guidance into cooperative and conflicting components. It preserves the cooperative component and adaptively attenuates only the conflicting one according to conflict strength. We further analyze conflict frequency and strength throughout generation to reveal how classifier guidance interacts with the generative process. CLEAR also dynamically identifies editable regions, constrains latent modifications, and directly preserves factual content outside them to reduce VAE-induced changes. Across five bidirectional tasks on two datasets, CLEAR retains latent-space efficiency while achieving counterfactual quality comparable to or better than strong image-space baselines, with a 2.5x speedup over the strongest baseline. Project page: https://yan-zen9.github.io/CLEAR/