Explaining image classifiers using statistical fault localization

Explaining image classifiers using statistical fault localization

The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for “Explainable AI”. In this paper, we show that statistical fault localization (SFL) techniques from software engineering deliver high quality explanations of...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Sun, Y, Chockler, H, Huang, X, Kroening, D
Format:	Conference item
Sprog:	English
Udgivet:	Springer 2020

Lignende værker

Probabilistic fault localisation
af: Landsberg, D, et al.
Udgivet: (2016)

Explainability and Transparency of Classifiers for Air-Handling Unit Faults Using Explainable Artificial Intelligence (XAI)
af: Molika Meas, et al.
Udgivet: (2022-08-01)

Coverage in interpolation-based model checking
af: Chockler, H, et al.
Udgivet: (2010)

Computing mutation coverage in interpolation-based model checking
af: Chockler, H, et al.
Udgivet: (2012)

Optimising spectrum based fault localisation for single fault programs using specifications
af: Landsberg, D, et al.
Udgivet: (2018)

Dependable modulation classifier explainer with measurable explainability
af: Gaurav Duggal, et al.
Udgivet: (2023-01-01)

Understanding Counterexamples with explain
af: Groce, A, et al.
Udgivet: (2004)

Explaining psychological statistics /
af: 218193 Cohen, Barry H.
Udgivet: (2008)

Statistics explained /
af: 368444 Hinton, Perry R. (Perry Roy), 1954-
Udgivet: (2004)

Explaining a deep learning based breast ultrasound image classifier with saliency maps
af: Byra Michał, et al.
Udgivet: (2022-04-01)

Detecting anomalies in blockchain transactions using machine learning classifiers and explainability analysis
af: Mohammad Hasan, et al.
Udgivet: (2024-09-01)

Cancer prediction using graph-based gene selection and explainable classifier
af: Mehrdad Rostami, et al.
Udgivet: (2022-04-01)

Classifying Faults Locations in Cable Terminations and Investigation of the Faults Reasons
af: V. Abbasi
Udgivet: (2018-09-01)

On the statistical assessment of classifiers using DNA microarray data
af: Carella M, et al.
Udgivet: (2006-08-01)

Explainable Deep Learning to Classify Royal Navy Ships
af: Bart Baesens, et al.
Udgivet: (2024-01-01)

The Use of Drone Photo Material to Classify the Purity of Photovoltaic Panels Based on Statistical Classifiers
af: Tomasz Czarnecki, et al.
Udgivet: (2022-01-01)

An Explainable Deep Learning Approach for Classifying Monkeypox Disease by Leveraging Skin Lesion Image Data
af: Andino Maseleno, et al.
Udgivet: (2024-10-01)

Weakly supervised segmentation models as explainable radiological classifiers for lung tumour detection on CT images
af: Robert O’Shea, et al.
Udgivet: (2023-11-01)

Interpretation of microbiota-based diagnostics by explaining individual classifier decisions
af: A. Eck, et al.
Udgivet: (2017-10-01)

Saliency-driven explainable deep learning in medical imaging: bridging visual explainability and statistical quantitative analysis
af: Yusuf Brima, et al.
Udgivet: (2024-06-01)

Improving Electrical Fault Detection Using Multiple Classifier Systems
af: José Oliveira, et al.
Udgivet: (2024-11-01)

Fault diagnosis of photovoltaic strings by using machine learning‐based stacking classifier
af: Bo Liu, et al.
Udgivet: (2024-02-01)

Localizing genes to cerebellar layers by classifying ISH images.
af: Lior Kirsch, et al.
Udgivet: (2012-01-01)

CLASSIFYING BENIGN AND MALIGNANT MASSES USING STATISTICAL MEASURES
af: B. Surendiran, et al.
Udgivet: (2011-11-01)

EXPLAINING A DEEP SPATIOTEMPORAL LAND COVER CLASSIFIER WITH ATTENTION AND REDESCRIPTION MINING
af: N. Méger, et al.
Udgivet: (2022-05-01)

Bearing Fault Diagnosis Based on Statistical Locally Linear Embedding
af: Xiang Wang, et al.
Udgivet: (2015-07-01)

Fault Identification of Rotor System Based on Classifying Time-Frequency Image Feature Tensor
af: Hui Li, et al.
Udgivet: (2017-01-01)

A fuzzy classifier system for fault tolerance
af: Mariela Cerrada, et al.
Udgivet: (2010-12-01)

Localization genus of classifying spaces
af: Yau, Donald Y. (Donald Ying Wai), 1977-
Udgivet: (2005)

Classifying Coding DNA with Nucleotide Statistics
af: Nicolas Carels, et al.
Udgivet: (2009-01-01)

Classifying Coding DNA with Nucleotide Statistics
af: Nicolas Carels, et al.
Udgivet: (2009-10-01)

Methodology for the Detection of Contamination and Gradual Outer Race Faults in Bearings by Fusion of Statistical Vibration–Current Features and SVM Classifier
af: Geovanni Díaz-Saldaña, et al.
Udgivet: (2024-06-01)

Exposing previously undetectable faults in deep neural networks
af: Dunn, I, et al.
Udgivet: (2021)

Multi-Fault Detection and Classification of Wind Turbines Using Stacking Classifier
af: Prince Waqas Khan, et al.
Udgivet: (2022-09-01)

Classification of Faults Operation of a Robotic Manipulator Using Symbolic Classifier
af: Nikola Anđelić, et al.
Udgivet: (2023-02-01)

Intelligent Classifiers in Distinguishing Transformer Faults Using Frequency Response Analysis
af: Mehdi Bigdeli, et al.
Udgivet: (2021-01-01)

Rock and fault rheology explain differences between on fault and distributed seismicity
af: C. Collettini, et al.
Udgivet: (2022-09-01)

Classifying blinking and winking EOG signals using statistical analysis and LSTM algorithm
af: Ahmed M. D. E. Hassanein, et al.
Udgivet: (2023-09-01)

Classification of electroencephalography signal using statistical features and regression classifier /
af: Nurbaity Sabri, 1985- author, et al.
Udgivet: (2014)

Model and Training Method of the Resilient Image Classifier Considering Faults, Concept Drift, and Adversarial Attacks
af: Viacheslav Moskalenko, et al.
Udgivet: (2022-10-01)