arXiv AI
Jun 2
A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
arXiv:2606. 01992v1 Announce Type: cross Abstract: Industrial anomaly detection has historically been a unimodal task.
IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generation
IAD-Unify is a unified architecture that connects a multimodal language model, a dense visual expert, and a diffusion editor via task‑specific token interfaces to perform industrial anomaly inspection tasks such as explaining defects, localizing pixels, and generating controlled edits. It uses a multi‑reference DINOv2 pathway to create a dense anomaly field, compresses it into structured evidence tokens, and feeds these tokens to Qwen3.5 for grounded answers and semantic residuals, while a separate query interface integrates with Stable Diffusion for localized generation. The system is trained in stages—first aligning dense evidence with language, then calibrating segmentation, and finally pre‑training the diffusion editor—while also building a large, quality‑controlled dataset of anomaly evidence and edit pairs.
Related stories
arXiv Computer Vision
Sep 25
Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
The paper introduces Anomaly‑LR, a defect‑grounded latent reasoning framework for industrial anomaly detection that builds a global understanding of an image and then refines anomaly‑relevant representations directly in visual latent space. It also presents IAD‑LR‑22K, a new instruction dataset with 22,228 image‑question pairs and detailed annotations. Experiments demonstrate that Anomaly‑LR outperforms comparable‑scale methods on multiple IAD benchmarks without needing external references or tools.
arXiv AI
Jul 22
OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation
arXiv:2607. 18850v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning.
arXiv AI
Jul 21
RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants
arXiv:2607. 16243v1 Announce Type: cross Abstract: Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories, enabling interactive vision-language-based querying.
arXiv Computer Vision
Sep 1
InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
arXiv:2608.29783v1 Announce Type: new Abstract: Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature di...
arXiv AI
Aug 13
Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
arXiv:2608. 11260v1 Announce Type: new Abstract: Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals.
arXiv Computer Vision
Sep 4
PL-SCEA: Reconfiguring Pretrained Attention for Few-Shot Industrial Anomaly Detection
The paper introduces PL‑SCEA, a method that reconfigures the attention mechanism of frozen Vision Foundation Models to better detect and localize anomalies in industrial images with few training examples. PL‑SCEA preserves the semantic context of pretrained query‑key attention while adding token‑adaptive self‑correlations over contextualized value features, then applies positive‑correlation filtering and power‑law reweighting to highlight task‑relevant relationships. The resulting features are fed into a lightweight variational autoencoder to produce reconstruction‑based anomaly scores, achieving competitive image‑level detection and strong pixel‑level localization on MVTec AD and VisA datasets.
arXiv Computer Vision
Aug 28
Aphanta: Diagnosing Task-Aligned Image-Edited Intermediates for Multimodal Reasoning
Aphanta is an automated framework that diagnoses how well image editors can produce task‑aligned visual intermediates for multimodal large language models (MLLMs). It evaluates three reasoning conditions—direct, editor‑generated, and idealized intermediate—to distinguish visual potential from practical editor performance across 20 tasks and various editor–MLLM pairs. The study finds that image editing benefits certain tasks like visual cue injection and grounding, but is less reliable for symbol‑sensitive or structural tasks, and demonstrates measurable performance gains with a Qwen pipeline.
arXiv Computer Vision
Oct 9
Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
The paper investigates whether in‑domain training alone can enable multimodal large language models (MLLMs) to perform fine‑grained industrial anomaly understanding (MM‑IAU). It shows that even specialized MLLMs fail to match human experts on defect localization and detection, and that combining different MLLMs does not eliminate this shortfall. To address this, the authors propose SiGMA, a spatially grounded multi‑agent framework that splits tasks among heterogeneous MLLM agents and a dedicated visual defect expert, achieving 85.2% accuracy on the MMAD benchmark—close to human performance and surpassing the best trained specialist.
arXiv Computer Vision
Oct 9
A Survey on Industrial Anomaly Synthesis
This survey reviews industrial anomaly synthesis (IAS), a field that has been underrepresented in prior studies focused on anomaly detection. It categorizes IAS methods into four paradigms—hand‑crafted, distribution‑hypothesis, generative model, and vision‑language model—while presenting a taxonomy that facilitates systematic comparison. The paper also discusses datasets, benchmarks, evaluation metrics, multimodal advances, and practical deployment considerations, offering guidance for future research.
arXiv AI
4d ago
Explainable Visual Anomaly Detection via Concept Bottleneck Models
The paper introduces Concept-Aware Visual Anomaly Detection (Concept-Aware VAD), a framework that extends Concept Bottleneck Models to visual anomaly detection. It offers dual-branch architecture: a concept branch for human-interpretable descriptions and a visual branch for pixel-level localization, evaluated on three VAD benchmarks with competitive performance. A user study shows higher effectiveness and lower misleading rates compared to state-of-the-art explainers, and concept-level interventions improve unsupervised detection.
arXiv AI
Sep 3
Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework
The paper introduces a new task called Quality Anomaly Perception for UGC Image Enhancement (UEAP) and presents the first benchmark dataset, UEAP-4k, featuring fine‑grained annotations of anomaly categories, locations, and severity levels in real‑world user‑generated content. It proposes the Difference‑Fusion Anomaly Perception Method (DFAP‑UGC), which fuses explicit differences between enhanced images and their references using dense spatial querying, regional verification, and quality‑aware ranking to robustly identify localized anomalies. A Locality‑Aware Dynamic Task Prioritization (LADTP) training strategy is also introduced to enable efficient end‑to‑end learning without multi‑stage overhead, and experiments demonstrate that DFAP‑UGC outperforms adapted classical baselines.