# Zero-shot Model Diagnosis

arXiv: https://arxiv.org/abs/2303.15441 · HTML: https://mlsanity.com/paper/2303.15441/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 38 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Editing in Style: Uncovering the Local Semantics of GANs](https://mlsanity.com/paper/2004.14367/) (2020)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)
- [SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing](https://mlsanity.com/paper/1906.07927/) (2019)
- [Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias](https://mlsanity.com/paper/1906.06439/) (2019)
- [Disentangling visual and written concepts in CLIP](https://mlsanity.com/paper/2206.07835/) (2022)
- [Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers](https://mlsanity.com/paper/1904.08489/) (2019)

## Built on by (most cited first, 23 of 23)

- [Number it: Temporal Grounding Videos like Flipping Manga](https://mlsanity.com/paper/2411.10332/) (2024)
- [LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images](https://mlsanity.com/paper/2305.19164/) (2023)
- [The Hidden Language of Diffusion Models](https://mlsanity.com/paper/2306.00966/) (2023)
- [Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach](https://mlsanity.com/paper/2309.07944/) (2023)
- [CLIP-QDA: An Explainable Concept Bottleneck Model](https://mlsanity.com/paper/2312.00110/) (2023)
- [Discover and Mitigate Multiple Biased Subgroups in Image Classifiers](https://mlsanity.com/paper/2403.12777/) (2024)
- [SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations](https://mlsanity.com/paper/2510.04398/) (2025)
- [Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data](https://mlsanity.com/paper/2310.10461/) (2023)
- [Benchmarking Segmentation Models with Mask-Preserved Attribute Editing](https://mlsanity.com/paper/2403.01231/) (2024)
- [Intersectional Unfairness Discovery](https://mlsanity.com/paper/2405.20790/) (2024)
- [Unsupervised Model Diagnosis](https://mlsanity.com/paper/2410.06243/) (2024)
- [Concept Lancet: Image Editing with Compositional Representation Transplant](https://mlsanity.com/paper/2504.02828/) (2025)
- [Contextual Knowledge Pursuit for Faithful Visual Synthesis](https://mlsanity.com/paper/2311.17898/) (2023)
- [Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals](https://mlsanity.com/paper/2505.12114/) (2025)
- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)
- [Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing](https://mlsanity.com/paper/2603.01535/) (2026)
- [Reinforcing Pre-trained Models Using Counterfactual Images](https://mlsanity.com/paper/2406.13316/) (2024)
- [Are Pose Estimators Ready for the Open World? STAGE: A GenAI Toolkit for Auditing 3D Human Pose Estimators](https://mlsanity.com/paper/2408.16536/) (2024)
- [Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations](https://mlsanity.com/paper/2511.20295/) (2025)
- [REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations](https://mlsanity.com/paper/2605.12813/) (2026)
- [Linking in Style: Understanding learned features in deep learning models](https://mlsanity.com/paper/2409.16865/) (2024)
- [Cross-modal Counterfactual Explanations: Uncovering Decision Factors and Dataset Biases in Subjective Classification](https://mlsanity.com/paper/2512.18864/) (2025)
- [Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs](https://mlsanity.com/paper/2604.08846/) (2026)

## Abstract (arXiv)

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. However, creating a balanced test set (i.e., one that is uniformly sampled over all the important traits) is often time-consuming, expensive, and prone to mistakes. The question we try to address is: can we evaluate the sensitivity of deep learning models to arbitrary visual attributes without an annotated test set? This paper argues the case that Zero-shot Model Diagnosis (ZOOM) is possible without the need for a test set nor labeling. To avoid the need for test sets, our system relies on a generative model and CLIP. The key idea is enabling the user to select a set of prompts (relevant to the problem) and our system will automatically search for semantic counterfactual images (i.e., synthesized images that flip the prediction in the case of a binary classifier) using the generative model. We evaluate several visual tasks (classification, key-point detection, and segmentation) in multiple visual domains to demonstrate the viability of our methodology. Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.