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%.
Vision foundation models have enabled strong training-free anomaly detection (AD). However, most existing approaches rely primarily on independent local patch features, leaving the global contextual information encoded by Vision Transformers (ViTs) underexploited.
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:2607. 23924v1 Announce Type: cross Abstract: Vision foundation models have enabled strong training-free anomaly detection (AD).
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 Spatial‑FAD, a few‑shot medical anomaly detection framework that fuses Vision‑Language Model (CLIP) semantics with spatial priors from Vision Foundation Models (DINO). A VFM‑enhanced adapter injects structural affinity into CLIP features, while a sliding‑window aggregation produces high‑resolution embeddings for finer lesion localization. Prototype‑enhanced support memory further improves efficiency and performance, yielding significant gains on Liver CT, Retinal OCT, and Brain MRI datasets, notably an 11.4% Dice improvement in 4‑shot scenarios.
arXiv:2608.23723v1 Announce Type: new Abstract: Few-shot anomaly detection (FSAD) has recently benefited from vision-language models such as CLIP, which enable anomaly de?tection by aligning visual f...
The paper identifies a problem in multi‑view anomaly detection called cross‑view information leakage, where fusing multiple inspection views can cause normal features to mask anomalies during reconstruction. To address this, the authors propose GLAD, a framework that uses a Global‑Local Attention Driven approach, combining vision foundation model features with two fusion modules: Multi‑view Merging Attention for local, weighted fusion and Object‑Guided Attention for global context aggregation. Experiments on Real‑IAD and MANTA‑Tiny demonstrate that GLAD outperforms existing methods across various metrics, underscoring the importance of restricting information flow to preserve the reconstruction gap.
CLIP is a powerful vision-language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt it with prompts or lightweight modules to increase...
The paper introduces SAGE, a lightweight method that guides decoder attention in vision-language models away from prompt‑invariant attention sinks (PIS) toward query‑dependent regions of interest (ROIs). By using token‑aligned ROI masks from vision backbones like CLIP, ViT, and DINOv3, SAGE improves visual grounding and reduces hallucinations across various VLM families. Experiments show consistent gains on public vision‑language benchmarks, especially in fine‑grained visual discrimination tasks where localized evidence is essential.
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
arXiv:2610.07689v1 Announce Type: new Abstract: Vision-Language Models (VLMs) such as CLIP excel in global semantic alignment but often lack fine-grained perceptual capabilities. This hinders dense p...
MEVL-STP introduces a two‑stage pipeline for spotting arbitrarily shaped scene text. The detection stage fuses features from six frozen vision encoders via a hierarchical Feature Pyramid Network and a Progressive Scale Expansion network to produce precise polygon masks. The recognition stage then crops these masks and feeds them to a fine‑tuned Qwen3‑VL‑8B‑Instruct model, achieving state‑of‑the‑art detection and end‑to‑end performance on CTW1500, Total‑Text, and ICDAR 2015 without synthetic pretraining.