paper-with-me

Papers

Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method

2021-01-26 · Satya M. Muddamsetty, Mohammad N. S. Jahromi, Andreea E. Ciontos, Laura M. Fenoy, Thomas B. Moeslund

Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of "black-box" models. In this paper, a novel XAI visual explanation algorithm known as the Similarity Difference and Uniqueness (SIDU) method that can effectively localize entire object regions responsible for prediction is presented in full detail. The SIDU algorithm robustness and effectiveness is analyzed through various computational and human subject experiments. In particular, the SIDU algorithm is assessed using three different types of evaluations (Application, Human and Functionally-Grounded) to demonstrate its superior performance. The robustness of SIDU is further studied in the presence of adversarial attack on "black-box" models to better understand its performance. Our code is available at: https://github.com/satyamahesh84/SIDU_XAI_CODE.

📄 PDF Abstract BibTeX arXiv:2101.10710

Code (1)

satyamahesh84/SIDU_XAI_CODE 공식 구현 tf

Tasks

Adversarial AttackExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Similar Papers 제목 키워드 기반

SIDU: Similarity Difference and Uniqueness Method for Explainable AI

2020-06-04 · Satya M. Muddamsetty, Mohammad N. S. Jahromi, Thomas B. Moeslund

A new brand of technical artificial intelligence ( Explainable AI ) research has focused on trying to open up the 'black box' and provide some explainability. This paper presents a novel visual explanation method for dee…

Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification

2020-12-14 · Martin Charachon, Céline Hudelot, Paul-Henry Cournède, Camille Ruppli 외

Explaining decisions of black-box classifiers is paramount in sensitive domains such as medical imaging since clinicians confidence is necessary for adoption. Various explanation approaches have been proposed, among whic…

General Classificationimage-classificationImage ClassificationMedical Image Classification

ProtoX: Explaining a Reinforcement Learning Agent via Prototyping

2022-11-06 · Ronilo J. Ragodos, Tong Wang, Qihang Lin, Xun Zhou

While deep reinforcement learning has proven to be successful in solving control tasks, the "black-box" nature of an agent has received increasing concerns. We propose a prototype-based post-hoc policy explainer, ProtoX,…

Contrastive LearningDeep Reinforcement LearningImitation Learningreinforcement-learning+3

A new Image Similarity Metric for a Perceptual and Transparent Geometric and Chromatic Assessment

2026-01-27 · Antonio Di Marino, Vincenzo Bevilacqua, Emanuel Di Nardo, Angelo Ciaramella 외 arxiv

In the literature, several studies have shown that state-of-the-art image similarity metrics are not perceptual metrics; moreover, they have difficulty evaluating images, especially when texture distortion is also presen…

Black-box Explanation of Object Detectors via Saliency Maps

2020-06-05 · CVPR 2021 1 · Vitali Petsiuk, Rajiv Jain, Varun Manjunatha, Vlad I. Morariu 외

We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object de…

Objectobject-detectionObject Detectionsoftware testing