GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection
cs.CV
Submitted: 2026-03-16
Updated: 2026-11-08
Code: https://github.com/gthpapadopoulos/GATE-AD
Terminology
Sources
- AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection
- APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences
- DINOv2: Learning Robust Visual Features without Supervision
- DINOv3
- FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detection
- Graph Attention Networks
- Search is All You Need for Few-shot Anomaly Detection
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs