UniDG introduces a unified defect generation framework that addresses the scarcity of abnormal samples in anomaly detection. By creating a large dataset of 300K normal‑abnormal‑mask‑caption quadruplets and formulating defect synthesis as Defect‑Context Editing, the model extracts reference defect context, organizes inputs in a diptych format, and fuses multimodal conditions via MM‑DiT attention. A two‑stage training strategy—Diversity‑SFT for transferable defect priors and optional Consistency‑RFT for reference adherence—enables UniDG to outperform prior few‑shot anomaly generation and editing baselines in both synthesis quality and downstream anomaly detection tasks without per‑category fine‑tuning.
arXiv:2610.07016v1 Announce Type: cross Abstract: In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to lear...
arXiv:2609.37314v1 Announce Type: new Abstract: Synthetic anomaly generation helps expand industrial anomaly datasets when real defects are scarce or unavailable. Existing approaches lie at two extre...
arXiv:2610.19610v1 Announce Type: new Abstract: Industrial anomaly detection (AD) is bottlenecked by the scarcity of anomalous samples, making high-fidelity anomaly synthesis crucial for improving do...
arXiv:2608.20713v1 Announce Type: new Abstract: Generative AI can now produce highly realistic images, yet current models still exhibit subtle but critical defects that undermine their reliability. W...
arXiv:2608. 00442v2 Announce Type: replace-cross Abstract: Medical anomaly detection identifies abnormal images and localizes lesions under scarce supervision while generalizing across organs and modalities.
The paper introduces DPA, a diffusion-based framework that decouples product-agnostic anomaly representations to enable zero-shot anomaly generation. By reusing real anomalies from existing source products and filtering them for plausibility, DPA learns product-irrelevant anomaly embeddings that can be transferred across products. An adaptive mask-guided pipeline and a training-free labeling module further refine the realism and localization of generated anomalies, leading to improved performance on MVTec-AD, VisA, and a new anomaly-transfer benchmark.
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.
The paper introduces Structured Defect Grounding (SDG), a method that treats text‑to‑image failure diagnosis as a structured set prediction problem, representing each defect as a tuple of location, type, reason, and importance. It presents SDG‑30K, a 30,000‑image dataset with box‑grounded annotations for four modern T2I generators, and a dedicated evaluation protocol, SDG‑Eval. Using a Vision‑Language Model as an SDG detector and a BoxFlow‑GRPO module, the authors demonstrate that SDG‑guided rewards improve diffusion model alignment and enable localized image refinement, positioning SDG as a unified interface for diagnosing and enhancing generative models.
arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...
VerdictAD is a training‑free framework that enhances existing few‑shot anomaly detectors by adding a typed decision model to evaluate query images and their local regions against a small set of normal references. It introduces two modules—Global Verdict Refinement (GVR) and Local Verdict Refinement (LVR)—which refine overall anomaly scores and anomaly maps, respectively, without generating text. When combined with a simple DINOv2‑based detector, VerdictAD consistently improves performance on MVTec AD, VisA, and MVTec LOCO AD across one‑shot and few‑shot settings.
Crane is a CLIP‑based framework for zero‑shot anomaly detection that enhances dense localization by adapting the vision encoder with a correlation‑based attention module and conditioning learnable prompts on global image context. It further fuses anomaly‑relevant patch features into the global representation for more sensitive image‑level detection, and a variant called Crane+ leverages DINOv2 spatial correlations for stronger pixel‑level performance. Across seven industrial benchmarks, Crane raises mean image‑level AP by 4.5% and Crane+ boosts mean pixel‑level AUPRO by 9.0%.
Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality.