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

arXiv: https://arxiv.org/abs/2501.01767 · HTML: https://mlsanity.com/paper/2501.01767/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 3 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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Asymmetric Student-Teacher Networks for Industrial Anomaly Detection](https://mlsanity.com/paper/2210.07829/) (2022)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection](https://mlsanity.com/paper/2005.14140/) (2020)
- [SatLM: Satisfiability-Aided Language Models Using Declarative Prompting](https://mlsanity.com/paper/2305.09656/) (2023)
- [Component-aware anomaly detection framework for adjustable and logical industrial visual inspection](https://mlsanity.com/paper/2305.08509/) (2023)
- [Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection](https://mlsanity.com/paper/2312.13783/) (2023)
- [LogiCode: an LLM-Driven Framework for Logical Anomaly Detection](https://mlsanity.com/paper/2406.04687/) (2024)

## Built on by (most cited first, 25 of 25)

- [AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection](https://mlsanity.com/paper/2504.11914/) (2025)
- [LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions](https://mlsanity.com/paper/2503.20252/) (2025)
- [LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection](https://mlsanity.com/paper/2504.12749/) (2025)
- [VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2503.23046/) (2025)
- [SALAD -- Semantics-Aware Logical Anomaly Detection](https://mlsanity.com/paper/2509.02101/) (2025)
- [AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation](https://mlsanity.com/paper/2512.13671/) (2025)
- [Foundation Models for Anomaly Detection: Vision and Challenges](https://mlsanity.com/paper/2502.06911/) (2025)
- [Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning](https://mlsanity.com/paper/2505.11945/) (2025)
- [Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models](https://mlsanity.com/paper/2604.07802/) (2026)
- [EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models](https://mlsanity.com/paper/2602.17419/) (2026)
- [M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection](https://mlsanity.com/paper/2603.00055/) (2026)
- [UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detection](https://mlsanity.com/paper/2606.20768/) (2026)
- [SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images](https://mlsanity.com/paper/2505.16659/) (2025)
- [Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection](https://mlsanity.com/paper/2506.18544/) (2025)
- [Explainable Visual Anomaly Detection via Concept Bottleneck Models](https://mlsanity.com/paper/2511.20088/) (2025)
- [SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2601.09147/) (2026)
- [Interpretable Logical Anomaly Classification via Constraint Decomposition and Instruction Fine-Tuning](https://mlsanity.com/paper/2602.03530/) (2026)
- [BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection](https://mlsanity.com/paper/2603.16645/) (2026)
- [Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge](https://mlsanity.com/paper/2604.23701/) (2026)
- [Fine-Tuning Vision-Language Models for Understanding Current Damage and Scoring Priority with Quality Guard Agent](https://mlsanity.com/paper/2605.27452/) (2026)
- [LADBench: A Benchmark for Logical Fault Detection in Images](https://mlsanity.com/paper/2606.17433/) (2026)
- [Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection](https://mlsanity.com/paper/2607.03817/) (2026)
- [Attention from Above: A Multimodal Model for Drone-Based Object Localization](https://mlsanity.com/paper/2607.17669/) (2026)
- [EmoLASP: Emotion Recognition with Language Models and Answer Set Programming](https://mlsanity.com/paper/2608.29035/) (2026)
- [Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomalies](https://mlsanity.com/paper/2610.18295/) (2026)

## 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.