1 code implementation • 11 Nov 2023 • Peng Wang, Haiming Yao, Wenyong Yu
Current unsupervised models struggle to strike a balance between detecting texture and object defects, lacking the capacity to discern latent representations and intricate features.
no code implementations • 31 Mar 2023 • Haiming Yao, Wei Luo, Wenyong Yu
In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection.
Ranked #15 on Anomaly Detection on MVTec LOCO AD
no code implementations • 10 Mar 2023 • Haiming Yao, Wenyong Yu, Wei Luo, Zhenfeng Qiang, Donghao Luo, Xiaotian Zhang
To address this issue, we propose a two-branch approach that consists of a local branch for detecting structural anomalies and a global branch for detecting logical anomalies.
Ranked #17 on Anomaly Detection on MVTec LOCO AD
no code implementations • 22 Nov 2022 • Haiming Yao, Wenyong Yu
To tackle the above limitations, we proposed a self-induction vision Transformer(SIVT) for unsupervised generalizable multi-category industrial visual anomaly detection and localization.
no code implementations • 18 Nov 2022 • Wei Luo, Haiming Yao, Wenyong Yu
Unlike most reconstruction-based methods, our NDP-Net first employs an encoding module that extracts multi scale discriminative features of the surface textures, which is augmented with the defect discriminative ability by the proposed artificial defects and the novel pixel-level defect perception loss.
no code implementations • 1 Nov 2022 • Haiming Yao, Xue Wang, Wenyong Yu
The extensive experiments conducted demonstrate that the proposed ST-MAE method can advance state-of-the-art performance on multiple benchmarks across application scenarios with a superior inference efficiency, which exhibits great potential to be the uniform model for unsupervised visual anomaly detection.
no code implementations • 8 Aug 2022 • Wei Luo, Tongzhi Niu, Lixin Tang, Wenyong Yu, Bin Li
At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds.
no code implementations • 22 Jun 2022 • Haiming Yao, Wenyong Yu, Xue Wang
Subsequently, a contrastive-learning-based memory feature module (CMFM) is proposed to obtain discriminative representations and construct a normal feature memory bank in the latent space, which can be employed as a substitute for defects and fast anomaly scores at the patch level.