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

arXiv: https://arxiv.org/abs/2501.16751 · HTML: https://mlsanity.com/paper/2501.16751/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [Distilling Model Failures as Directions in Latent Space](https://mlsanity.com/paper/2206.14754/) (2022)
- [Learning Concise and Descriptive Attributes for Visual Recognition](https://mlsanity.com/paper/2308.03685/) (2023)
- [The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models](https://mlsanity.com/paper/2107.00758/) (2021)
- [OvarNet: Towards Open-vocabulary Object Attribute Recognition](https://mlsanity.com/paper/2301.09506/) (2023)
- [Adaptive Testing of Computer Vision Models](https://mlsanity.com/paper/2212.02774/) (2022)
- [Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches](https://mlsanity.com/paper/2102.05897/) (2021)
- [FACTS: First Amplify Correlations and Then Slice to Discover Bias](https://mlsanity.com/paper/2309.17430/) (2023)
- [AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.17373/) (2024)
- [Identification of Systematic Errors of Image Classifiers on Rare Subgroups](https://mlsanity.com/paper/2303.05072/) (2023)
- [Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms](https://mlsanity.com/paper/2306.08167/) (2023)
- [VLSlice: Interactive Vision-and-Language Slice Discovery](https://mlsanity.com/paper/2309.06703/) (2023)

## Built on by (most cited first, 11 of 11)

- [ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts](https://mlsanity.com/paper/2510.26186/) (2025)
- [FailureAtlas:Mapping the Failure Landscape of T2I Models via Active Exploration](https://mlsanity.com/paper/2509.21995/) (2025)
- [Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions](https://mlsanity.com/paper/2502.12360/) (2025)
- [textitFocaLogic: Logic-Based Interpretation of Visual Model Decisions](https://mlsanity.com/paper/2601.12049/) (2026)
- [Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models](https://mlsanity.com/paper/2606.09046/) (2026)
- [SafeFix: Targeted Model Repair via Controlled Image Generation](https://mlsanity.com/paper/2508.08701/) (2025)
- [GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks](https://mlsanity.com/paper/2512.24592/) (2025)
- [Efficient Cross-Country Data Acquisition Strategy for ADAS via Street-View Imagery](https://mlsanity.com/paper/2602.01836/) (2026)
- [CB-SLICE: Concept-Based Interpretable Error Slice Discovery](https://mlsanity.com/paper/2605.29836/) (2026)
- [Do Not Forget the Obvious - RISC: A Risk-Informed Slice-Coverage Protocol for Safe Autonomous Driving](https://mlsanity.com/paper/2608.12051/) (2026)
- [Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions](https://mlsanity.com/paper/2609.11126/) (2026)

## Abstract (arXiv)

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.