Research map / Image generation / GANs
Diffeomorphic Counterfactuals With Generative Models
Ann-Kathrin Dombrowski, Jan E. Gerken, Klaus‐Robert Müller, Pan Kessel
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 changed | Where | Measured | Effect |
|---|---|---|---|
| perform gradient ascent in flow latent space Z instead of input space X | counterfactual generation · MNIST | IM1: 1.603 -> 1.056 | Improved |
| perform gradient ascent in flow latent space Z instead of input space X | counterfactual generation · CelebA | IM1: 1.144 -> 0.807 | Improved |
| perform gradient ascent in latent space Z instead of input space X | helix toy example · Helix toy example | median distance to data manifold: 2.34 -> 0.01 | Improved |
| gradient ascent in Z instead of X | counterfactual generation · CelebA | L2 distance to source image in Z: 473.72 -> 138.35 | Improved |
| gradient ascent in Z instead of X | counterfactual generation · CheXpert | L2 distance to source image in Z: 355.50 -> 64.90 | Improved |
| gradient ascent in Z instead of X | counterfactual generation · MNIST | L2 distance to source image in Z: 41.86 -> 35.26 | Improved |
| gradient ascent in Z instead of X | counterfactual generation · CelebA | L2 distance to source image in X: 2.84 -> 19.10 | Hurt |
| gradient ascent in Z instead of X | counterfactual generation · MNIST | L2 distance to source image in X: 2.54 -> 4.82 | Hurt |
| use approximate diffeomorphism (cVAE/GAN) instead of exact flow | approximate diffeomorphic counterfactuals · CelebA | qualitative background fidelity | Hurt |
Closest papers by meaning
- Counterfactual Maps: What They Are and How to Find Them (NeurIPS 2026 · similarity 0.86)
- DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control (NeurIPS 2025 · similarity 0.86)
- CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations (NeurIPS 2026 · similarity 0.85)
- Counterfactual reasoning: an analysis of in-context emergence (NeurIPS 2025 · similarity 0.85)
- Counterfactual Generative Modeling with Variational Causal Inference (ICLR 2025 · similarity 0.84)
- Robust Stochastic Graph Generator for Counterfactual Explanations (AAAI 2024 · similarity 0.84)
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.
