no code implementations • 19 Apr 2024 • Junbiao Pang, Baocheng Xiong, Jiaqi Wu
In this paper, we address these problems from a view that utilizes contexts of the cracks and propose an end-to-end deep learning method to model the context information flow.
no code implementations • 17 Apr 2024 • Junbiao Pang, Zailin Dong, Jiaxin Deng, Mengyuan Zhu, Yunwei Zhang
Based on the keypoints detection, we propose a symbol grouping method to redraw the rectangle symbols in CAD images.
no code implementations • 27 Mar 2024 • Jiaqi Wu, Junbiao Pang, Baochang Zhang, Qingming Huang
Semi-supervised learning (SSL) is a practical challenge in computer vision.
no code implementations • 24 Feb 2024 • Jiaxin Deng, Junbiao Pang, Baochang Zhang, Tian Wang
Concretely, we discover that the gradient of SAM is a combination of the gradient of SGD and the Projection of the Second-order gradient matrix onto the First-order gradient (PSF).
no code implementations • 21 Feb 2024 • Junbiao Pang, Tianyang Cai, Baochang Zhang, Jiaqi Wu, Ye Tao
Existing Quantization-Aware Training (QAT) methods intensively depend on the complete labeled dataset or knowledge distillation to guarantee the performances toward Full Precision (FP) accuracies.
no code implementations • 3 Nov 2023 • Jiaqi Wu, Junbiao Pang, Qingming Huang
Semi-supervised pose estimation is a practically challenging task for computer vision.
1 code implementation • 3 Nov 2023 • Jiaqi Wu, Junbiao Pang, Qingming Huang
Both semi-supervised classification and regression are practically challenging tasks for computer vision.