AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding

2024-01-12

AI Summary

Automatically identifying and attributing performance-deficient data slices (i.e., subpopulations) in unlabeled, unstructured image data remains challenging due to the absence of metadata and interpretable diagnostics. Method: This paper proposes a metadata-agnostic data slicing framework that jointly leverages gradient-based class attribution maps and clustering-driven slice discovery; introduces Attribution Mosaic—a novel visual analytics technique for slice-level attribution interpretation; and integrates a human-in-the-loop analysis pipeline with a plug-and-play attribution-consistency regularization mechanism for end-to-end model repair. Results: Evaluated on two benchmark vision datasets, the method achieves an average 5.2% improvement in slice-level accuracy, enables users to complete bias diagnosis and mitigation within 10 minutes, and reduces reliance on manual annotations by over 90%. Its core contributions are the first metadata-free, interpretable slice discovery method, attribution-driven visual analytics, and a deployable, end-to-end repair pipeline.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Adversarial Learning & Robustness
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance, often characterized by distinct feature sets or descriptive metadata. However, in the context of validating vision models involving unstructured image data, this approach faces significant challenges, including the laborious and costly requirement for additional metadata and the complex task of interpreting the root causes of underperformance. To address these challenges, we introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for metadata-free data slice finding. Our system identifies interpretable data slices that involve common model behaviors and visualizes these patterns through an Attribution Mosaic design. Our interactive interface provides straightforward guidance for users to detect, interpret, and annotate predominant model issues, such as spurious correlations (model biases) and mislabeled data, with minimal effort. Additionally, it employs a cutting-edge model regularization technique to mitigate the detected issues and enhance the model's performance. The efficacy of AttributionScanner is demonstrated through use cases involving two benchmark datasets, with qualitative and quantitative evaluations showcasing its substantial effectiveness in vision model validation, ultimately leading to more reliable and accurate models.

Problem

• Identify poor performance subgroups in datasets.
• Validate vision models without additional metadata.
• Detect and mitigate model issues like biases.

Innovation

• Metadata-free data slice finding
• Attribution Mosaic visualization design
• Model regularization technique enhancement