1 code implementation • 25 Jun 2023 • Lin Wang, Xiufen Ye, Liqiang Zhu, Weijie Wu, JianGuo Zhang, Huiming Xing, Chao Hu
Notably, there is a lack of research on the application of SAM to sonar imaging.
no code implementations • 25 Dec 2022 • Chao Hu, Jian Yao, Weijie Wu, Weibin Qiu, Liqiang Zhu
Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics.
no code implementations • 3 Dec 2022 • Chao Hu, Liqiang Zhu, Weibing Qiu, Weijie Wu
Firstly, to enhance the model's processing ability for different scale targets, a multi-scale perception module based on dilated convolution is designed, and the depth features containing multi-scale information are re-refined from both spatial and channel directions considering the inconsistency between feature maps of different scales.
no code implementations • 23 Nov 2022 • Chao Hu, Liqiang Zhu, Weibin Qiu, Weijie Wu
Recently, the vision transformer (ViT) has made breakthroughs in image recognition.
no code implementations • 18 Nov 2022 • Chao Hu, Liqiang Zhu
Aiming at the problem that the current video anomaly detection cannot fully use the temporal information and ignore the diversity of normal behavior, an anomaly detection method is proposed to integrate the spatiotemporal information of pedestrians.
no code implementations • 10 Nov 2022 • Chao Hu, Liqiang Zhu
Then, the semantic features of the motion representation are obtained through the local attention mechanism in the motion guidance module to obtain the high-level semantic features of the appearance representation.
no code implementations • 18 Oct 2022 • Chao Hu, Weibin Qiu, Weijie Wu, Liqiang Zhu
Motion features are used multiple targets in the video frame to construct spatial context simultaneously, re-encoding the target appearance and motion features, and finally reconstructing the above features through the spatio-temporal dual-stream network, and using the reconstruction error to represent the abnormal score.
no code implementations • 10 Dec 2018 • Wei Wang, Liqiang Zhu
To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps.