# VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2110.13252 · HTML: https://mlsanity.com/paper/2110.13252/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 60 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.06032/) (2019)
- [Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models](https://mlsanity.com/paper/1908.01224/) (2019)
- [An Analysis of Deep Neural Network Models for Practical Applications](https://mlsanity.com/paper/1605.07678/) (2016)
- [Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations](https://mlsanity.com/paper/1904.02323/) (2019)
- [Do Convolutional Neural Networks Learn Class Hierarchy?](https://mlsanity.com/paper/1710.06501/) (2017)
- [Towards Better Analysis of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.07043/) (2016)
- [Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models](https://mlsanity.com/paper/1808.00196/) (2018)
- [A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes](https://mlsanity.com/paper/2009.06876/) (2020)
- [CNNComparator: Comparative Analytics of Convolutional Neural Networks](https://mlsanity.com/paper/1710.05285/) (2017)
- [A Visual Analytics System for Multi-model Comparison on Clinical Data Predictions](https://mlsanity.com/paper/2002.10998/) (2020)
- [Competitive Inner-Imaging Squeeze and Excitation for Residual Network](https://mlsanity.com/paper/1807.08920/) (2018)

## Built on by (most cited first, 11 of 11)

- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Visual Analytics For Machine Learning: A Data Perspective Survey](https://mlsanity.com/paper/2307.07712/) (2023)
- [ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.21233/) (2025)
- [Stop Misusing t-SNE and UMAP for Visual Analytics](https://mlsanity.com/paper/2506.08725/) (2025)
- [AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding](https://mlsanity.com/paper/2401.06462/) (2024)
- [Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments](https://mlsanity.com/paper/2408.03274/) (2024)
- [Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods](https://mlsanity.com/paper/2508.12730/) (2025)
- [A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series](https://mlsanity.com/paper/2405.03234/) (2024)
- [VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels](https://mlsanity.com/paper/2507.09008/) (2025)
- [A Comparative Visual Analytics Framework for Evaluating Evolutionary Processes in Multi-objective Optimization](https://mlsanity.com/paper/2308.05640/) (2023)
- [TopoAlign: Topology-Aware Visual Representation Alignment](https://mlsanity.com/paper/2605.25541/) (2026)

## Abstract (arXiv)

The rapid development of Convolutional Neural Networks (CNNs) in recent years has triggered significant breakthroughs in many machine learning (ML) applications. The ability to understand and compare various CNN models available is thus essential. The conventional approach with visualizing each model's quantitative features, such as classification accuracy and computational complexity, is not sufficient for a deeper understanding and comparison of the behaviors of different models. Moreover, most of the existing tools for assessing CNN behaviors only support comparison between two models and lack the flexibility of customizing the analysis tasks according to user needs. This paper presents a visual analytics system, VAC-CNN (Visual Analytics for Comparing CNNs), that supports the in-depth inspection of a single CNN model as well as comparative studies of two or more models. The ability to compare a larger number of (e.g., tens of) models especially distinguishes our system from previous ones. With a carefully designed model visualization and explaining support, VAC-CNN facilitates a highly interactive workflow that promptly presents both quantitative and qualitative information at each analysis stage. We demonstrate VAC-CNN's effectiveness for assisting novice ML practitioners in evaluating and comparing multiple CNN models through two use cases and one preliminary evaluation study using the image classification tasks on the ImageNet dataset.