mlsanityData to 7 Oct 2026

VisCUIT: Visual Auditor for Bias in CNN Image Classifier

arXiv 2204.05899 ↗First posted 12 Apr 2022cs.CV cs.HC cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

CNN image classifiers are widely used, thanks to their efficiency and accuracy. However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inapplicable to general image classification tasks or require significant user efforts in perusing all data subgroups to manually specify which data attributes to inspect. We present VisCUIT, an interactive visualization system that reveals how and why a CNN classifier is biased. VisCUIT visually summarizes the subgroups on which the classifier underperforms and helps users discover and characterize the cause of the underperformances by revealing image concepts responsible for activating neurons that contribute to misclassifications. VisCUIT runs in modern browsers and is open-source, allowing people to easily access and extend the tool to other model architectures and datasets. VisCUIT is available at the following public demo link: https://poloclub.github.io/VisCUIT. A video demo is available at https://youtu.be/eNDbSyM4R_4.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 12 Apr 2022.

Builds on

33 of 63 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  9. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  10. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  11. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  12. 2018Deep Face Recognition: A Surveycited by 275
21 more
  1. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  2. 2018Aequitas: A Bias and Fairness Audit Toolkitcited by 145
  3. 2019Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learningcited by 145
  4. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 128
  5. 2019FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learningcited by 93
  6. 2020Demographic Bias in Biometrics: A Survey on an Emerging Challengecited by 93
  7. 2020Don't Judge an Object by Its Context: Learning to Overcome Contextual Biascited by 91
  8. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  9. 2020Mitigating Face Recognition Bias via Group Adaptive Classifiercited by 67
  10. 2020Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacycited by 61
  11. 2019Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?cited by 56
  12. 2020Analysis of Gender Inequality In Face Recognition Accuracycited by 47
  13. 2019Overfitting of neural nets under class imbalance: Analysis and improvements for segmentationcited by 27
  14. 2021UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Modelscited by 23
  15. 2019Advancements in Image Classification using Convolutional Neural Networkcited by 20
  16. 2020Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networkscited by 12
  17. 2014Face Recognition Methods & Applicationscited by 11
  18. 2019CUP: Cluster Pruning for Compressing Deep Neural Networkscited by 7
  19. 2021Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profilescited by 6
  20. 2021Dataset Bias Mitigation Through Analysis of CNN Training Scorescited by 2
  21. 2021Guided Hyperparameter Tuning Through Visualization and Inferencecited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 2.

8 papers.

  1. 2023Discovering and Mitigating Visual Biases through Keyword Explanationcited by 58
  2. 2024Fairness and Bias Mitigation in Computer Vision: A Surveycited by 12
  3. 2023Angler: Helping Machine Translation Practitioners Prioritize Model Improvementscited by 11
  4. 2024AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Findingcited by 6
  5. 2025VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysiscited by 5
  6. 2025Attention IoU: Examining Biases in CelebA using Attention Mapscited by 3
  7. 2023Variation of Gender Biases in Visual Recognition Models Before and After Finetuningcited by 2
  8. 2022Interactive Visual Feature Searchcited by 0