GenAU augments a vision-language model with segmentation tokens to unify image-level anomaly detection, pixel-level segmentation, multi-type classification, and language-based defect analysis in a single instruction-following architecture.
Multiads: Defect-aware supervision for multi- type anomaly detection and segmentation in zero-shot learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
AD-Copilot trains an MLLM on a new curated industrial dataset Chat-AD with a Comparison Encoder that uses cross-attention on image pairs, reaching 82.3% accuracy on MMAD and 3.35x gains on MMAD-BBox while generalizing and exceeding human experts on some tasks.
citing papers explorer
-
GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models
GenAU augments a vision-language model with segmentation tokens to unify image-level anomaly detection, pixel-level segmentation, multi-type classification, and language-based defect analysis in a single instruction-following architecture.
-
AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
AD-Copilot trains an MLLM on a new curated industrial dataset Chat-AD with a Comparison Encoder that uses cross-attention on image pairs, reaching 82.3% accuracy on MMAD and 3.35x gains on MMAD-BBox while generalizing and exceeding human experts on some tasks.