mlsanityData to 14 Oct 2026

Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis

arXiv 2603.21213 ↗First posted 22 Mar 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Counterfactual image generation enables controlled data augmentation, bias mitigation, and disease modeling. However, existing methods guided by external classifiers or regressors are limited to subject-level factors (e.g., age) and fail to produce localized structural changes, often resulting in global artifacts. Pixel-level guidance using segmentation masks has been explored, but requires user-defined counterfactual masks, which are tedious and impractical. Segmentor-guided Counterfactual Fine-Tuning (Seg-CFT) addressed this by using segmentation-derived measurements to supervise structure-specific variables, yet it remains restricted to global interventions. We propose Positional Seg-CFT, which subdivides each structure into regional segments and derives independent measurements per region, enabling spatially localized and anatomically coherent counterfactuals. Experiments on coronary CT angiography show that Pos-Seg-CFT generates realistic, region-specific modifications, providing finer spatial control for modeling disease progression.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

19 of 28 references.

References · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  3. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 98
  4. 2022Deep End-to-end Causal Inferencecited by 95
  5. 2022Diffusion Models for Causal Discovery via Topological Orderingcited by 66
  6. 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 57
  7. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  8. 2023Measuring axiomatic soundness of counterfactual image modelscited by 34
  9. 2024Counterfactual Image Editingcited by 20
  10. 2024Robust image representations with counterfactual contrastive learningcited by 14
  11. 2024Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessmentcited by 13
  12. 2023Debiasing Counterfactuals In the Presence of Spurious Correlationscited by 12
7 more
  1. 2024Mitigating attribute amplification in counterfactual image generationcited by 12
  2. 2024Counterfactual contrastive learning: robust representations via causal image synthesiscited by 11
  3. 2025Diffusion Counterfactual Generation with Semantic Abductioncited by 10
  4. 2025CF-Seg: Counterfactuals meet Segmentationcited by 10
  5. 2024MedEdit: Counterfactual Diffusion-based Image Editing on Brain MRIcited by 8
  6. 2024Semi-Supervised Learning for Deep Causal Generative Modelscited by 6
  7. 2025Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesiscited by 2

Built on by

Not cited yet.