most citedAnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

8 citations · 19 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024★ 1 cited

Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control

Yue Han, Junwei Zhu, Keke He +7

Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities…

cs.CV2024★ 1 cited

SCL: Towards Domain Generalization via Single-Temporal Multimodal Contrastive Learning for Remote Sensing Change Detection

Qiangang Du, Jinlong Peng, Xu Chen +4

In recent years, change detection and anomaly detection models based on CNN and transformer have achieved remarkable success across various datasets based on paired data. However,…

cs.CV2024

Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection

Qiangang Du, Jinlong Peng, Changan Wang +6

Change detection aims to identify remote sense object changes by analyzing data between bitemporal image pairs. Due to the large temporal and spatial span of data collection in cha…

cs.CV2024★ 2 cited

DMAD: Dual Memory Bank for Real-World Anomaly Detection

Jianlong Hu, Xu Chen, Zhenye Gan +7

Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency. However, t…

cs.CV2023★ 7 cited

DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection

Haoyang He, Jiangning Zhang, Hongxu Chen +6

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have…

cs.CV2023★ 8 cited

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

Teng Hu, Jiangning Zhang, Ran Yi +5

Anomaly inspection plays an important role in industrial manufacture. Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data. Althoug…