# Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1908.02686 · HTML: https://mlsanity.com/paper/1908.02686/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2019.

## Built on by (most cited first, 30 of 49)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)
- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [FIND: A Function Description Benchmark for Evaluating Interpretability Methods](https://mlsanity.com/paper/2309.03886/) (2023)
- [OCTET: Object-aware Counterfactual Explanations](https://mlsanity.com/paper/2211.12380/) (2022)
- [Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis](https://mlsanity.com/paper/2104.10252/) (2021)
- [Towards Better Explanations for Object Detection](https://mlsanity.com/paper/2306.02744/) (2023)
- [Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation](https://mlsanity.com/paper/2103.14332/) (2021)
- [Spatial-temporal Concept based Explanation of 3D ConvNets](https://mlsanity.com/paper/2206.05275/) (2022)
- [ODAM: Gradient-based instance-specific visual explanations for object detection](https://mlsanity.com/paper/2304.06354/) (2023)
- [Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization](https://mlsanity.com/paper/2507.10846/) (2025)
- [Probabilistic Stability Guarantees for Feature Attributions](https://mlsanity.com/paper/2504.13787/) (2025)
- [Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP](https://mlsanity.com/paper/2502.18816/) (2025)
- [NeuralMVS: Bridging Multi-View Stereo and Novel View Synthesis](https://mlsanity.com/paper/2108.03880/) (2021)
- ["Is your explanation stable?": A Robustness Evaluation Framework for Feature Attribution](https://mlsanity.com/paper/2209.01782/) (2022)
- [Making a Bird AI Expert Work for You and Me](https://mlsanity.com/paper/2112.02747/) (2021)
- [SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation](https://mlsanity.com/paper/2411.01710/) (2024)
- [Improving Attribution Methods by Learning Submodular Functions](https://mlsanity.com/paper/2104.09073/) (2021)
- [MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope](https://mlsanity.com/paper/2302.05294/) (2023)
- [Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations](https://mlsanity.com/paper/2303.09171/) (2023)
- [Locally Interpretable One-Class Anomaly Detection for Credit Card Fraud Detection](https://mlsanity.com/paper/2108.02501/) (2021)
- [Fine-Grained Visual Entailment](https://mlsanity.com/paper/2203.15704/) (2022)
- [Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution](https://mlsanity.com/paper/2104.06629/) (2021)
- [Spatio-Temporal Perturbations for Video Attribution](https://mlsanity.com/paper/2109.00222/) (2021)
- [Explainable, automated urban interventions to improve pedestrian and vehicle safety](https://mlsanity.com/paper/2110.11672/) (2021)
- [TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency](https://mlsanity.com/paper/2110.05182/) (2021)
- [Gradient Frequency Modulation for Visually Explaining Video Understanding Models](https://mlsanity.com/paper/2111.01215/) (2021)
- [Overview of Class Activation Maps for Visualization Explainability](https://mlsanity.com/paper/2309.14304/) (2023)
- [HyenaPixel: Global Image Context with Convolutions](https://mlsanity.com/paper/2402.19305/) (2024)

## Abstract (arXiv)

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.