# Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks Source: [Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:43:30.383Z Authors: J\\"org Wagner, Jan Mathias K\\"ohler, Tobias Gindele, Leon Hetzel, Jakob Thadd\\"aus Wiedemer, Sven Behnke Published: 2019-08-07T15:39:55.000Z ## Abstract To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explanation method, which highlights the evidence in the input image for a specific prediction. Our approach is based on a novel technique to defend against adversarial evidence (i.e. faulty evidence due to artefacts) by filtering gradients during optimization. The defense does not depend on human-tuned parameters. It enables explanations which are both fine-grained and preserve the characteristics of images, such as edges and colors. The explanations are interpretable, suited for visualizing detailed evidence and can be tested as they are valid model inputs. We qualitatively and quantitatively evaluate our approach on a multitude of models and datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Saliency Map Faithfulness Evaluation on ILSVRC 2012 (val)](): Saliency Map Faithfulness Evaluation; ILSVRC 2012 (val); Deletion Score: 0.0644. ## Original sources and implementation [Original paper]() [PDF]()