# FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection

arXiv: https://arxiv.org/abs/2609.02212 · HTML: https://mlsanity.com/paper/2609.02212/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 2 Sep 2026.

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

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2407.15795/) (2024)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization](https://mlsanity.com/paper/2407.09359/) (2024)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2502.07601/) (2025)
- [Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector](https://mlsanity.com/paper/1901.10609/) (2019)
- [Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector](https://mlsanity.com/paper/2402.03094/) (2024)
- [Towards Robust Pattern Recognition: A Review](https://mlsanity.com/paper/2006.06976/) (2020)
- [Active learning for data streams: a survey](https://mlsanity.com/paper/2302.08893/) (2023)
- [Plug and Play Active Learning for Object Detection](https://mlsanity.com/paper/2211.11612/) (2022)
- [An Incremental Unified Framework for Small Defect Inspection](https://mlsanity.com/paper/2312.08917/) (2023)
- [Coreset Selection for Object Detection](https://mlsanity.com/paper/2404.09161/) (2024)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics](https://mlsanity.com/paper/2310.17316/) (2023)
- [MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism](https://mlsanity.com/paper/2503.01463/) (2025)
- [Few-shot Defect Image Generation based on Consistency Modeling](https://mlsanity.com/paper/2408.00372/) (2024)
- [Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning](https://mlsanity.com/paper/2508.02293/) (2025)
- [Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection](https://mlsanity.com/paper/2503.16125/) (2025)
- [MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation](https://mlsanity.com/paper/2602.07011/) (2026)
- [Classification Committee for Active Deep Object Detection](https://mlsanity.com/paper/2308.08476/) (2023)

## Abstract (arXiv)

Ensuring the reliability of deep learning models in real-time industrial defect detection is critical for high-stakes quality inspection. To mine uncertain samples within continuous industrial media streams, thereby enhancing the reliability of the detection system, this paper proposes a streaming active learning method based on the Fuzzy Dual-dimensional Uncertainty (FuDU) framework. Specifically, we first design a Prototype-based Global Uncertainty Quantification (PGUQ) module on the backbone to evaluate image-level uncertainty via normal/defective feature prototypes. A Dual-entropy defect Uncertainty Evaluator (DeUE) is then integrated into the detection head to quantify box-level uncertainty. Finally, by modeling uncertainty as systematic error, we propose a fuzzy dual-dimensional uncertainty-aware strategy that leverages fuzzy inference to fuse dual-dimensional uncertainties, enabling expert knowledge-driven adaptive sampling decisions. Comprehensive experiments demonstrate that FuDU is efficient and flexible, making it well-suited for challenging industrial inspection tasks such as the detection of nuclear fuel rod defects. Our code is publicly available at: https://github.com/wangzhaoyang-508/FuDU.