Contrastive Counterfactual Visual Explanations With Overdetermination
A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an average of 27% using a novel pointing game metric. CLEAR Image excels in identifying cases of "causal overdetermination" where there are multiple patches in an image, any one of which is sufficient by itself to cause the classification probability to be close to one.
Code (1)
Tasks
counterfactualMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generating Counterfactual and Contrastive Explanations using SHAP
With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two spec…
counterfactualDecision MakingCausal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Dataset
In this paper, we propose leveraging causal generative learning as an interpretable tool for explaining image classifiers. Specifically, we present a generative counterfactual inference approach to study the influence of…
AttributecounterfactualCounterfactual ExplanationCounterfactual InferenceCounterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks
Explaining deep models in a human-understandable way has been explored by many works that mostly explain why an input causes a corresponding prediction (ie., Why P?). However, seldom they could handle those more comp…
counterfactualKACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference
In order to better understand the reason behind model behaviors (i.e., making predictions), most recent works have exploited generative models to provide complementary explanations. However, existing approaches in NLP ma…
counterfactualLanguage ModellingNatural Language InferenceTowards Counterfactual and Contrastive Explainability and Transparency of DCNN Image Classifiers
Explainability of deep convolutional neural networks (DCNNs) is an important research topic that tries to uncover the reasons behind a DCNN model's decisions and improve their understanding and reliability in high-risk e…
counterfactual