2 code implementations • 8 Apr 2024 • Yufeng Yue, Yinan Deng, Jiahui Wang, Yi Yang
Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying.
no code implementations • 15 Mar 2024 • Qin Xu, Sitong Li, Jiahui Wang, Bo Jiang, Jinhui Tang
To tackle this challenge, we propose a weakly supervised Context-Semantic Quality Awareness Network (CSQA-Net) for FGVC.
Ranked #4 on Fine-Grained Image Classification on NABirds
Fine-Grained Image Classification Fine-Grained Visual Categorization
1 code implementation • 14 Mar 2024 • Yinan Deng, Jiahui Wang, Jingyu Zhao, Xinyu Tian, Guangyan Chen, Yi Yang, Yufeng Yue
In this work, we propose OpenGraph, the first open-vocabulary hierarchical graph representation designed for large-scale outdoor environments.
no code implementations • 28 Nov 2023 • Jiahui Wang, Qin Xu, Bo Jiang, Bin Luo
Label propagation methods try to propagate the labels of support samples on the constructed graph encoding the relationships between both support and query samples.
no code implementations • 22 Nov 2023 • Shilin Zhang, Jiahui Wang
CL, especially the Class Incremental Learning, enables adaptation to new test distributions while continuously learning from a single-pass training data stream, which is more in line with the practical application requirements of real-world scenarios.
1 code implementation • 18 Aug 2023 • Binhao Ma, Jiahui Wang, Dejun Wang, Bo Meng
DFB is unique in its independence from training data access, requiring solely the knowledge of a specific target class.
no code implementations • 22 Feb 2023 • Jiyuan Kuang, Yabin Gao, Yizhuo Sun, Jiahui Wang, Aohua Liu, Yue Zhao, Jianxing Liu
In anothor word, the settling time under the presented controller is independent of the initial conditions and equals the prescribed time instant.
no code implementations • 21 Feb 2023 • Jiahui Wang, Haiyue Zhu, Haoren Guo, Abdullah Al Mamun, Cheng Xiang, Tong Heng Lee
Moreover, a case study on practical CAM/CAD segmentation is presented to demonstrate the effectiveness of our approach for real-world applications.
1 code implementation • IEEE Transactions on Multimedia 2023 • Qin Xu, Jiahui Wang, Bo Jiang, Bin Luo
The proposed IELT involves three main modules: multi-head voting (MHV) module, cross-layer refinement (CLR) module, and dynamic selection (DS) module.
no code implementations • 4 Jul 2022 • Jiahui Wang, Haiyue Zhu, Haoren Guo, Abdullah Al Mamun, Vadakkepat Prahlad, Tong Heng Lee
However, the disadvantage is that the resulting models from the fully-supervised learning methodology are highly reliant on the completeness of the available dataset, and its generalization ability is relatively poor to new unknown segmentation types (i. e. further additional novel classes).
no code implementations • 4 Jul 2022 • Haoren Guo, Haiyue Zhu, Jiahui Wang, Vadakkepat Prahlad, Weng Khuen Ho, Tong Heng Lee
With the availability of deep learning approaches, the great potential and prospect of utilizing these for RUL prediction have resulted in several models which are designed driven by operation data of manufacturing machines.
1 code implementation • 19 May 2022 • Jiahui Wang, Zhenyou Wang, Shanna Zhuang, Hui Wang
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers.
Ranked #5 on Action Segmentation on Breakfast
no code implementations • 28 Apr 2022 • Miloš Nikolić, Enrique Torres Sanchez, Jiahui Wang, Ali Hadi Zadeh, Mostafa Mahmoud, Ameer Abdelhadi, Andreas Moshovos
We introduce a software-hardware co-design approach to reduce memory traffic and footprint during training with BFloat16 or FP32 boosting energy efficiency and execution time performance.