no code implementations • 7 Feb 2024 • Mingxuan Liu, Jiankai Tang, Haoxiang Li, Jiahao Qi, Siwei Li, Kegang Wang, Yuntao Wang, Hong Chen
Additionally, the power consumption of the transformer block is reduced by a factor of 12. 2, while maintaining decent performance as PhysFormer and other ANN-based models.
no code implementations • 12 Oct 2023 • Xingyue Liu, Jiahao Qi, Chen Chen, Kangcheng Bin, Ping Zhong
Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features.
no code implementations • 16 Jul 2022 • Jiahao Qi, Zhiqiang Gong, Xingyue Liu, Kangcheng Bin, Chen Chen, YongQian Li, Wei Xue, Yu Zhang, Ping Zhong
Deep learning methodology contributes a lot to the development of hyperspectral image (HSI) analysis community.
1 code implementation • 25 May 2022 • Zhiqiang Gong, Ping Zhong, Jiahao Qi, Panhe Hu
Finally, the CNN with noise inclined module and the denoise framework is developed to obtain discriminative features and provides good classification performance of hyperspectral image.
no code implementations • 19 May 2022 • Yu Zhang, Zhiqiang Gong, Yichuang Zhang, YongQian Li, Kangcheng Bin, Jiahao Qi, Wei Xue, Ping Zhong
Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples.
no code implementations • 8 Jan 2022 • Aihuan Yao, Jiahao Qi, Ping Zhong
Extensive experiments are conducted on UAV-VeID dataset, and our method achieves the best performance compared with recent ReID works.