Pith. sign in

REVIEW 5 cited by

Counterfactual Generative Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2101.06046 v1 pith:UDGZDMQF submitted 2021-01-15 cs.LG cs.CV

Axel Sauer , Andreas Geiger This is my paper · ORCID
classification cs.LGcs.CV
keywords classificationcounterfactualgenerativeimagesmodelobjecttaskbackground
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object shape, deep classifiers tend to exploit spurious correlations with low-level texture or the background for solving the classification task. In this work, we take a step towards more robust and interpretable classifiers that explicitly expose the task's causal structure. Building on current advances in deep generative modeling, we propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background; hence, they allow for generating counterfactual images. We demonstrate the ability of our model to generate such images on MNIST and ImageNet. Further, we show that the counterfactual images can improve out-of-distribution robustness with a marginal drop in performance on the original classification task, despite being synthetic. Lastly, our generative model can be trained efficiently on a single GPU, exploiting common pre-trained models as inductive biases.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision

    cs.LG 2026-01 conditional novelty 6.0 of 10

    XFACTORS separates latent factors into per-factor subspaces with InfoNCE supervision, achieving near-perfect FactorVAE scores on synthetic benchmarks and qualitative factor swapping on CelebA.

  2. Diffusion Counterfactual Generation with Semantic Abduction

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Diffusion-based causal image counterfactuals with semantic abduction improve identity preservation at a small cost in intervention effectiveness, demonstrated on Morpho-MNIST, CelebA-HQ, and mammogram artifact removal.

  3. Concept-based Visual Counterfactual Explanations with Diffusion Models

    cs.AI 2026-05 conditional novelty 5.0 of 10

    C-VCE embeds a concept-bottleneck classifier inside a diffusion generator so counterfactual edits are steered by interpretable attributes and a gradient mask, beating L-DVCE on proximity and realism but not on flip ra...

  4. Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models

    cs.CV 2024-12 conditional novelty 5.0 of 10

    DiffEx explains classifier decisions by using a vision-language model to build a hierarchical semantic corpus and a beam-search algorithm to rank which visual attributes, alone or in combination, most influence classi...

  5. GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective

    cs.AI 2025-07 unverdicted novelty 3.0 of 10

    A position paper claiming that generative-AI agents that model and predict multi-agent dynamics will replace today's reactive MARL approaches.

Pith tools