mlsanityData to 14 Oct 2026

An Incremental Unified Framework for Small Defect Inspection

arXiv 2312.08917 ↗First posted 14 Dec 2023cs.CV cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing. Yet, many methods, tailored to specific pipelines, grapple with diverse product portfolios and evolving processes. Addressing this, we present the Incremental Unified Framework (IUF), which can reduce the feature conflict problem when continuously integrating new objects in the pipeline, making it advantageous in object-incremental learning scenarios. Employing a state-of-the-art transformer, we introduce Object-Aware Self-Attention (OASA) to delineate distinct semantic boundaries. Semantic Compression Loss (SCL) is integrated to optimize non-primary semantic space, enhancing network adaptability for novel objects. Additionally, we prioritize retaining the features of established objects during weight updates. Demonstrating prowess in both image and pixel-level defect inspection, our approach achieves state-of-the-art performance, proving indispensable for dynamic and scalable industrial inspections. Our code will be released at https://github.com/jqtangust/IUF.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

26 of 45 references.

References · 26

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  3. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  4. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  6. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  7. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  9. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
  10. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  11. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  12. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
14 more
  1. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  2. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  3. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  4. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  5. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  6. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  7. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  8. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  9. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  10. 2020ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgettingcited by 85
  11. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  12. 2023Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semanticscited by 16
  13. 2022A Continual Learning Framework for Adaptive Defect Classification and Inspectioncited by 7
  14. 2022A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 12; 2026: 11.

25 papers.

Sort:

By area:

  1. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  2. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  3. 2025LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimizationcited by 16
  4. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  5. 2025ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detectioncited by 9
  6. 2025Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detectioncited by 7
  7. 2025Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detectioncited by 4
  8. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  9. 2024ONER: Online Experience Replay for Incremental Anomaly Detectioncited by 3
  10. 2025C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisorcited by 3
  11. 2025BeltCrack: the First Sequential-image Industrial Conveyor Belt Crack Detection Dataset and Its Baseline with Triple-domain Feature Learningcited by 2
  12. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categoriescited by 2
13 more
  1. 2025Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Conceptscited by 1
  2. 2025MECAD: A multi-expert architecture for continual anomaly detectioncited by 1
  3. 2026Continual Learning of Domain-Invariant Representationscited by 1
  4. 2026Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Bankscited by 1
  5. 2026Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?cited by 1
  6. 2026CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detectioncited by 1
  7. 2025Class Incremental Medical Image Segmentation via Prototype-Guided Calibration and Dual-Aligned Distillationcited by 0
  8. 2026AdapTS: Lightweight Teacher-Student Approach for Multi-Class and Continual Visual Anomaly Detectioncited by 0
  9. 2026Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditionscited by 0
  10. 2026DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detectioncited by 0
  11. 2026Memory-Bounded Continuation of Greedy Sampling for Continual Anomaly Detectioncited by 0
  12. 2026FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detectioncited by 0
  13. 2026Neural-Collapse-guided Task-Free Continual Anomaly Detectioncited by 0