paper-with-me

홈 › Papers

Counterfactual Explanations on Robust Perceptual Geodesics

2026-01-26 · Eslam Zaher, Maciej Trzaskowski, Quan Nguyen, Fred Roosta arxiv

Latent-space optimization methods for counterfactual explanations - framed as minimal semantic perturbations that change model predictions - inherit the ambiguity of Wachter et al.'s objective: the choice of distance metric dictates whether perturbations are meaningful or adversarial. Existing approaches adopt flat or misaligned geometries, leading to off-manifold artifacts, semantic drift, or adversarial collapse. We introduce Perceptual Counterfactual Geodesics (PCG), a method that constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric induced from robust vision features. This geometry aligns with human perception and penalizes brittle directions, enabling smooth, on-manifold, semantically valid transitions. Experiments on three vision datasets show that PCG outperforms baselines and reveals failure modes hidden under standard metrics.

📄 PDF Abstract BibTeX arXiv:2601.18678

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Relatable Explainable AI with the Perceptual Process

2021-12-28 · Wencan Zhang, Brian Y. Lim

Machine learning models need to provide contrastive explanations, since people often seek to understand why a puzzling prediction occurred instead of some expected outcome. Current contrastive explanations are rudimentar…

counterfactualEmotion RecognitionExplainable Artificial Intelligence (XAI)

Explaining Classifiers using Adversarial Perturbations on the Perceptual Ball

2019-12-19 · CVPR 2021 1 · Andrew Elliott, Stephen Law, Chris Russell

We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations…

counterfactual

LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations

2025-09-10 · Payal Varshney, Adriano Lucieri, Christoph Balada, Sheraz Ahmed 외 arxiv

Video-based AI systems are increasingly adopted in safety-critical domains such as autonomous driving and healthcare. However, interpreting their decisions remains challenging due to the inherent spatiotemporal complexit…

Action RecognitionAutonomous Driving

Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution

2024-05-16 · Eslam Zaher, Maciej Trzaskowski, Quan Nguyen, Fred Roosta

In this paper, we dive into the reliability concerns of Integrated Gradients (IG), a prevalent feature attribution method for black-box deep learning models. We particularly address two predominant challenges associated …

ECINN: Efficient Counterfactuals from Invertible Neural Networks

2021-03-25 · Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent

Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We propose a method, ECINN, that utilizes the…

counterfactualimage-classificationImage Classification