HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging

TL;DR

HiBug2 is an automated framework that efficiently discovers and repairs error slices in deep learning models, improving robustness and interpretability across various computer vision tasks.

Contribution

It introduces a novel, interpretable process for generating visual attributes and an efficient algorithm for systematic error slice discovery, extending capabilities to predict slices beyond validation data.

Findings

Improves error slice coherence and precision

Enhances model robustness through targeted repairs

Effective across multiple vision domains

Abstract

Despite the significant success of deep learning models in computer vision, they often exhibit systematic failures on specific data subsets, known as error slices. Identifying and mitigating these error slices is crucial to enhancing model robustness and reliability in real-world scenarios. In this paper, we introduce HiBug2, an automated framework for error slice discovery and model repair. HiBug2 first generates task-specific visual attributes to highlight instances prone to errors through an interpretable and structured process. It then employs an efficient slice enumeration algorithm to systematically identify error slices, overcoming the combinatorial challenges that arise during slice exploration. Additionally, HiBug2 extends its capabilities by predicting error slices beyond the validation set, addressing a key limitation of prior approaches. Extensive experiments across multiple domains, including image classification, pose estimation, and object detection - show that HiBug2 not only improves the coherence and precision of identified error slices but also significantly enhances the model repair capabilities.