mlsanityData to 14 Oct 2026

Strategies to exploit XAI to improve classification systems

arXiv 2306.05801 ↗First posted 9 Jun 2023cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Explainable Artificial Intelligence (XAI) aims to provide insights into the decision-making process of AI models, allowing users to understand their results beyond their decisions. A significant goal of XAI is to improve the performance of AI models by providing explanations for their decision-making processes. However, most XAI literature focuses on how to explain an AI system, while less attention has been given to how XAI methods can be exploited to improve an AI system. In this work, a set of well-known XAI methods typically used with Machine Learning (ML) classification tasks are investigated to verify if they can be exploited, not just to provide explanations but also to improve the performance of the model itself. To this aim, two strategies to use the explanation to improve a classification system are reported and empirically evaluated on three datasets: Fashion-MNIST, CIFAR10, and STL10. Results suggest that explanations built by Integrated Gradients highlight input features that can be effectively used to improve classification performance.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 18 of its 28 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

18 of 28 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  8. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  9. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 407
  10. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
  11. 2016Rationalizing Neural Predictionscited by 281
  12. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 250
6 more
  1. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 142
  2. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  3. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  4. 2018TED: Teaching AI to Explain its Decisionscited by 33
  5. 2022Toward the application of XAI methods in EEG-based systemscited by 6
  6. 2021Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systemscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 1.

7 papers.

  1. 2025Recent Advances in Medical Image Classificationcited by 2
  2. 2024SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencodercited by 1
  3. 2024Towards a general framework for improving the performance of classifiers using XAI methodscited by 0
  4. 2024XAI-based Feature Ensemble for Enhanced Anomaly Detection in Autonomous Driving Systemscited by 0
  5. 2025IMPACTX: improving model performance by appropriately constraining the training with teacher explanationscited by 0
  6. 2025Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Trainingcited by 0
  7. 2026Instance-Adaptive Parametrization for Amortized Variational Inferencecited by 0