Counterfactual Explanations on Robust Perceptual Geodesics
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Towards Relatable Explainable AI with the Perceptual Process
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
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…
counterfactualLD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations
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 DrivingManifold Integrated Gradients: Riemannian Geometry for Feature Attribution
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
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