arXiv Computer Vision August 24, 2026 By Alireza Salehi, Mohammadreza Salehi, Reshad Hosseini, Cees G. M. Snoek, Makoto Yamada, Mohammad Sabokrou

Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection

Read the original on arXiv Computer Vision →

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%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Hugging Face Trending Papers

Jul 27

DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection

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.

llms rag benchmarks

arXiv AI

Jul 28

DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection

arXiv:2607. 23924v1 Announce Type: cross Abstract: Vision foundation models have enabled strong training-free anomaly detection (AD).

By Jyun-Ze Tang, Po-Han Huang, Ming-Ching Chang, Chih-Fan Hsu, Jeng-Lin Li

llms rag benchmarks

arXiv AI

Aug 11

Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection

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.

By Yibo Wan, Jinyu Cai, See-kiong Ng

computer-vision efficiency benchmarks safety

arXiv Machine Learning

Jun 2

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

arXiv:2606. 01710v1 Announce Type: cross Abstract: Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification.

By Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie, Sarah Erfani

llms rag fine-tuning multimodal benchmarks safety

arXiv AI

Jul 31

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions

arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.

By Xinran Liu, Shouqian Shi, Yutong Chen, Ge Wang, Xin-Wei Yao, Sheng Zhong

rag computer-vision multimodal benchmarks safety

arXiv Machine Learning

Jul 2

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

arXiv:2602. 21397v2 Announce Type: replace-cross Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights.

By Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani

llms rag multimodal benchmarks safety

One email a morning, machine-written

Related stories

DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection

DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection

Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation