Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Tian, Guanzhong"'
This study explores the recently proposed challenging multi-view Anomaly Detection (AD) task. Single-view tasks would encounter blind spots from other perspectives, resulting in inaccuracies in sample-level prediction. Therefore, we introduce the \te
Externí odkaz:
http://arxiv.org/abs/2407.11935
Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
Autor:
Zhang, Jiangning, Wang, Chengjie, Li, Xiangtai, Tian, Guanzhong, Xue, Zhucun, Liu, Yong, Pang, Guansong, Tao, Dacheng
Anomaly detection (AD) is often focused on detecting anomaly areas for industrial quality inspection and medical lesion examination. However, due to the specific scenario targets, the data scale for AD is relatively small, and evaluation metrics are
Externí odkaz:
http://arxiv.org/abs/2404.10760
Autor:
He, Haoyang, Bai, Yuhu, Zhang, Jiangning, He, Qingdong, Chen, Hongxu, Gan, Zhenye, Wang, Chengjie, Li, Xiangtai, Tian, Guanzhong, Xie, Lei
Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Mamba-based models,
Externí odkaz:
http://arxiv.org/abs/2404.06564
Few-shot anomaly detection (FSAD) plays a crucial role in industrial manufacturing. However, existing FSAD methods encounter difficulties leveraging a limited number of normal samples, frequently failing to detect and locate inconspicuous anomalies i
Externí odkaz:
http://arxiv.org/abs/2403.04151
Autor:
Chen, Xuhai, Zhang, Jiangning, Tian, Guanzhong, He, Haoyang, Zhang, Wuhao, Wang, Yabiao, Wang, Chengjie, Liu, Yong
This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects. We propose a framework called CLIP-AD to leverage the zero-shot capabilities of the large vision-language model CLIP. Firstly, we reint
Externí odkaz:
http://arxiv.org/abs/2311.00453
The field of cooperative multi-agent reinforcement learning (MARL) has seen widespread use in addressing complex coordination tasks. While value decomposition methods in MARL have been popular, they have limitations in solving tasks with non-monotoni
Externí odkaz:
http://arxiv.org/abs/2307.02200
Publikováno v:
Pattern Recognition 2023
Neural network quantization is a very promising solution in the field of model compression, but its resulting accuracy highly depends on a training/fine-tuning process and requires the original data. This not only brings heavy computation and time co
Externí odkaz:
http://arxiv.org/abs/2307.00498
Deep neural networks have been widely used in medical image analysis and medical image segmentation is one of the most important tasks. U-shaped neural networks with encoder-decoder are prevailing and have succeeded greatly in various segmentation ta
Externí odkaz:
http://arxiv.org/abs/2306.04905
Autor:
Liu, Liang, Zhang, Boshen, Zhang, Jiangning, Zhang, Wuhao, Gan, Zhenye, Tian, Guanzhong, Zhu, Wenbing, Wang, Yabiao, Wang, Chengjie
Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing semi-supervi
Externí odkaz:
http://arxiv.org/abs/2303.09061
Publikováno v:
In Pattern Recognition Letters October 2023 174:78-84
