mlsanityData to 14 Oct 2026

fAIlureNotes: Supporting Designers in Understanding the Limits of AI Models for Computer Vision Tasks

arXiv 2302.11703 ↗First posted 22 Feb 2023cs.LG cs.CV cs.HCcited by 10

Not on the map. Why?

Abstract (arXiv)

To design with AI models, user experience (UX) designers must assess the fit between the model and user needs. Based on user research, they need to contextualize the model's behavior and potential failures within their product-specific data instances and user scenarios. However, our formative interviews with ten UX professionals revealed that such a proactive discovery of model limitations is challenging and time-intensive. Furthermore, designers often lack technical knowledge of AI and accessible exploration tools, which challenges their understanding of model capabilities and limitations. In this work, we introduced a failure-driven design approach to AI, a workflow that encourages designers to explore model behavior and failure patterns early in the design process. The implementation of fAIlureNotes, a designer-centered failure exploration and analysis tool, supports designers in evaluating models and identifying failures across diverse user groups and scenarios. Our evaluation with UX practitioners shows that fAIlureNotes outperforms today's interactive model cards in assessing context-specific model performance.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 37 of its 93 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

37 of 93 references.

References · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  7. 2015Fast R-CNNcited by 2,933
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  9. 2018Datasheets for Datasetscited by 1,386
  10. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  11. 2018Model Cards for Model Reportingcited by 1,080
  12. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
25 more
  1. 2021Dynabench: Rethinking Benchmarking in NLPcited by 459
  2. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 372
  3. 2017Adversarial Attacks on Neural Network Policiescited by 320
  4. 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 216
  5. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  6. 2019Gradio: Hassle-Free Sharing and Testing of ML Models in the Wildcited by 178
  7. 2022Domino: Discovering Systematic Errors with Cross-Modal Embeddingscited by 156
  8. 2015End-to-end people detection in crowded scenescited by 140
  9. 2019The Ethics of AI Ethics -- An Evaluation of Guidelinescited by 129
  10. 2019Artificial Intelligence: the global landscape of ethics guidelinescited by 107
  11. 2020Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Databasecited by 96
  12. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  13. 2018Automated Data Slicing for Model Validation:A Big data - AI Integration Approachcited by 70
  14. 2022Interactive Model Cards: A Human-Centered Approach to Model Documentationcited by 61
  15. 2018Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failurecited by 49
  16. 2021Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffscited by 48
  17. 2018FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformitycited by 31
  18. 2021Discovering and Validating AI Errors With Crowdsourced Failure Reportscited by 28
  19. 2017Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loopcited by 26
  20. 2021Towards A Process Model for Co-Creating AI Experiencescited by 18
  21. 2022Symphony: Composing Interactive Interfaces for Machine Learningcited by 18
  22. 2021Nine Potential Pitfalls when Designing Human-AI Co-Creative Systemscited by 12
  23. 2021Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspectivecited by 9
  24. 2020CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphscited by 3
  25. 2023Wizard of Errors: Introducing and Evaluating Machine Learning Errors in Wizard of Oz Studiescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 1; 2026: 2.

10 papers.

  1. 2023Investigating Practices and Opportunities for Cross-functional Collaboration around AI Fairness in Industry Practicecited by 15
  2. 2023Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithmscited by 9
  3. 2023PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflowscited by 8
  4. 2023Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytellingcited by 7
  5. 2024Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviorscited by 5
  6. 2026Situated, Dynamic, and Subjective: Envisioning the Design of Theory-of-Mind-Enabled Everyday AI with Industry Practitionerscited by 1
  7. 2024Human-Centered AI Product Prototyping with No-Code AutoML: Conceptual Framework, Potentials and Limitationscited by 0
  8. 2024Documentation Practices of Artificial Intelligencecited by 0
  9. 2025Exploring the Innovation Opportunities for Pre-trained Modelscited by 0
  10. 2026"I Just Need GPT to Refine My Prompts": Rethinking Onboarding and Help-Seeking with Generative 3D Modeling Toolscited by 0