Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image Classification

arXiv:2405.03301v1 Announce Type: new
Abstract: Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific class is identified, without providing a detailed explanation of the model's decision process. Striving to address such a need, we introduce a post-hoc method that explains the entire feature extraction process of a Convolutional Neural Network. These explanations include a layer-wise representation of the …

abstract art arxiv biases class classification cnn cs.cv cs.lg errors explainability generate human image loop machine machine learning machine learning models maps network show state transparency trust type