mlsanityData to 7 Oct 2026

LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction

arXiv 2501.01767 ↗First posted 3 Jan 2025cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Logical image understanding involves interpreting and reasoning about the relationships and consistency within an image's visual content. This capability is essential in applications such as industrial inspection, where logical anomaly detection is critical for maintaining high-quality standards and minimizing costly recalls. Previous research in anomaly detection (AD) has relied on prior knowledge for designing algorithms, which often requires extensive manual annotations, significant computing power, and large amounts of data for training. Autoregressive, multimodal Vision Language Models (AVLMs) offer a promising alternative due to their exceptional performance in visual reasoning across various domains. Despite this, their application to logical AD remains unexplored. In this work, we investigate using AVLMs for logical AD and demonstrate that they are well-suited to the task. Combining AVLMs with format embedding and a logic reasoner, we achieve SOTA performance on public benchmarks, MVTec LOCO AD, with an AUROC of 86.0% and F1-max of 83.7%, along with explanations of anomalies. This significantly outperforms the existing SOTA method by a large margin.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 3 Jan 2025.

Builds on

25 of 39 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  8. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  9. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  10. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 786
  11. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  12. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
13 more
  1. 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Taskscited by 499
  2. 2024LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Modelscited by 394
  3. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  4. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  5. 2023Teaching CLIP to Count to Tencited by 194
  6. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
  7. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  8. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  9. 2024The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinismcited by 113
  10. 2023SatLM: Satisfiability-Aided Language Models Using Declarative Promptingcited by 100
  11. 2023Component-aware anomaly detection framework for adjustable and logical industrial visual inspectioncited by 22
  12. 2023Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detectioncited by 19
  13. 2024LogiCode: an LLM-Driven Framework for Logical Anomaly Detectioncited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 13.

24 papers.

Sort:

By area:

  1. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  2. 2025LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detectioncited by 9
  3. 2025LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questionscited by 8
  4. 2025VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous Drivingcited by 4
  5. 2025AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentationcited by 4
  6. 2025Foundation Models for Anomaly Detection: Vision and Challengescited by 3
  7. 2025Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuningcited by 3
  8. 2025SALAD -- Semantics-Aware Logical Anomaly Detectioncited by 3
  9. 2026EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Modelscited by 2
  10. 2026M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detectioncited by 1
  11. 2026UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detectioncited by 1
  12. 2025SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Imagescited by 0
12 more
  1. 2025Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detectioncited by 0
  2. 2025Explainable Visual Anomaly Detection via Concept Bottleneck Modelscited by 0
  3. 2026SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detectioncited by 0
  4. 2026Interpretable Logical Anomaly Classification via Constraint Decomposition and Instruction Fine-Tuningcited by 0
  5. 2026BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detectioncited by 0
  6. 2026Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Modelscited by 0
  7. 2026Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judgecited by 0
  8. 2026Fine-Tuning Vision-Language Models for Understanding Current Damage and Scoring Priority with Quality Guard Agentcited by 0
  9. 2026LADBench: A Benchmark for Logical Fault Detection in Imagescited by 0
  10. 2026Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detectioncited by 0
  11. 2026Attention from Above: A Multimodal Model for Drone-Based Object Localizationcited by 0
  12. 2026EmoLASP: Emotion Recognition with Language Models and Answer Set Programmingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
  2. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
  3. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  4. 2026Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
  5. 2025Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
  6. 2025ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoning
  7. 2026Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
  8. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models