# Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks

arXiv: https://arxiv.org/abs/1712.06302 · HTML: https://mlsanity.com/paper/1712.06302/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2017.

## Built on by (most cited first, 28 of 28)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods](https://mlsanity.com/paper/2308.06248/) (2023)
- [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021)
- [Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis](https://mlsanity.com/paper/2303.14836/) (2023)
- [ODAM: Gradient-based instance-specific visual explanations for object detection](https://mlsanity.com/paper/2304.06354/) (2023)
- [Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention](https://mlsanity.com/paper/2204.04601/) (2022)
- [Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing](https://mlsanity.com/paper/2209.03268/) (2022)
- [Benchmarking the Attribution Quality of Vision Models](https://mlsanity.com/paper/2407.11910/) (2024)
- [Accurate Explanation Model for Image Classifiers using Class Association Embedding](https://mlsanity.com/paper/2406.07961/) (2024)
- [Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector](https://mlsanity.com/paper/2407.19308/) (2024)
- [Explainable AI needs formalization](https://mlsanity.com/paper/2409.14590/) (2024)
- [Precise Benchmarking of Explainable AI Attribution Methods](https://mlsanity.com/paper/2308.03161/) (2023)
- [MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization](https://mlsanity.com/paper/2104.14375/) (2021)
- [Convolutional Neural Network Interpretability with General Pattern Theory](https://mlsanity.com/paper/2102.04247/) (2021)
- [Automatic Infectious Disease Classification Analysis with Concept Discovery](https://mlsanity.com/paper/2209.02415/) (2022)
- [How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?](https://mlsanity.com/paper/2310.18496/) (2023)
- [FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors](https://mlsanity.com/paper/2405.12601/) (2024)
- [Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed](https://mlsanity.com/paper/2104.07954/) (2021)
- [On The Coherence of Quantitative Evaluation of Visual Explanations](https://mlsanity.com/paper/2302.10764/) (2023)
- [CE-FAM: Concept-Based Explanation via Fusion of Activation Maps](https://mlsanity.com/paper/2509.23849/) (2025)
- [Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception](https://mlsanity.com/paper/2512.05937/) (2025)
- [Exploring SAIG Methods for an Objective Evaluation of XAI](https://mlsanity.com/paper/2602.08715/) (2026)
- [Towards the Characterization of Representations Learned via Capsule-based Network Architectures](https://mlsanity.com/paper/2305.05349/) (2023)
- [FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks](https://mlsanity.com/paper/2305.10121/) (2023)
- [Active Globally Explainable Learning for Medical Images via Class Association Embedding and Cyclic Adversarial Generation](https://mlsanity.com/paper/2306.07306/) (2023)
- [Deep Model Interpretation with Limited Data : A Coreset-based Approach](https://mlsanity.com/paper/2410.00524/) (2024)
- [A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods](https://mlsanity.com/paper/2609.30397/) (2026)

## Abstract (arXiv)

Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations. We interpret the model through average visualizations of this reduced set of features. Then, at test time, we explain the network prediction by accompanying the predicted class label with supporting visualizations derived from the identified features. In addition, we propose a method to address the artifacts introduced by stridded operations in deconvNet-based visualizations. Moreover, we introduce an8Flower, a dataset specifically designed for objective quantitative evaluation of methods for visual explanation.Experiments on the MNIST,ILSVRC12,Fashion144k and an8Flower datasets show that our method produces detailed explanations with good coverage of relevant features of the classes of interest