Unsupervised Model Diagnosis
| Autor: | Wang, Yinong Oliver, Li, Eileen, Luo, Jinqi, Wang, Zhaoning, De la Torre, Fernando |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Ensuring model explainability and robustness is essential for reliable deployment of deep vision systems. Current methods for evaluating robustness rely on collecting and annotating extensive test sets. While this is common practice, the process is labor-intensive and expensive with no guarantee of sufficient coverage across attributes of interest. Recently, model diagnosis frameworks have emerged leveraging user inputs (e.g., text) to assess the vulnerability of the model. However, such dependence on human can introduce bias and limitation given the domain knowledge of particular users. This paper proposes Unsupervised Model Diagnosis (UMO), that leverages generative models to produce semantic counterfactual explanations without any user guidance. Given a differentiable computer vision model (i.e., the target model), UMO optimizes for the most counterfactual directions in a generative latent space. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources, such as dictionaries or language models. We validate the framework on multiple vision tasks (e.g., classification, segmentation, keypoint detection). Extensive experiments show that our unsupervised discovery of semantic directions can correctly highlight spurious correlations and visualize the failure mode of target models without any human intervention. Comment: 9 pages, 9 figures, 3 tables |
| Databáze: | arXiv |
| Externí odkaz: |
|