no code implementations • 31 Mar 2023 • Tao Bai, Chen Chen, Lingjuan Lyu, Jun Zhao, Bihan Wen
Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real world.
no code implementations • 19 Dec 2022 • Yonghao Xu, Tao Bai, Weikang Yu, Shizhen Chang, Peter M. Atkinson, Pedram Ghamisi
Recent advances in artificial intelligence (AI) have significantly intensified research in the geoscience and remote sensing (RS) field.
no code implementations • 19 Jul 2022 • Xiongkun Linghu, Yan Bai, Yihang Lou, Shengsen Wu, Jinze Li, Jianzhong He, Tao Bai
Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning.
no code implementations • 3 Jul 2022 • Jinze Li, Yan Bai, Yihang Lou, Xiongkun Linghu, Jianzhong He, Shaoyun Xu, Tao Bai
The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem.
no code implementations • CVPR 2022 • Liang Chen, Yihang Lou, Jianzhong He, Tao Bai, Minghua Deng
Therefore, in this paper, we propose a Geometric anchor-guided Adversarial and conTrastive learning framework with uncErtainty modeling called GATE to alleviate these issues.
Ranked #5 on Universal Domain Adaptation on Office-Home
no code implementations • 19 Nov 2021 • Tao Bai, Jun Zhao, Jinlin Zhu, Shoudong Han, Jiefeng Chen, Bo Li, Alex Kot
Through extensive experiments, AI-GAN achieves high attack success rates, outperforming existing methods, and reduces generation time significantly.
no code implementations • 15 Oct 2021 • Tao Bai, Jun Zhao, Lanqing Guo, Bihan Wen
Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment.
no code implementations • 7 Aug 2021 • Shengsen Wu, Liang Chen, Yihang Lou, Yan Bai, Tao Bai, Minghua Deng, Lingyu Duan
Therefore, backward-compatible representation is proposed to enable "new" features to be compared with "old" features directly, which means that the database is active when there are both "new" and "old" features in it.
no code implementations • 29 Jun 2021 • Tao Bai, Jinqi Luo, Jun Zhao
The patches are encouraged to be consistent with the background images with adversarial training while preserving strong attack abilities.
no code implementations • 2 Feb 2021 • Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen, Qian Wang
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models.
no code implementations • 3 Nov 2020 • Tao Bai, Jinqi Luo, Jun Zhao
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN).
no code implementations • 21 Sep 2020 • Tao Bai, Jinnan Chen, Jun Zhao, Bihan Wen, Xudong Jiang, Alex Kot
In this paper, we propose a novel approach called Guided Adversarial Contrastive Distillation (GACD), to effectively transfer adversarial robustness from teacher to student with features.
no code implementations • 21 Sep 2020 • Jinqi Luo, Tao Bai, Jun Zhao
Through extensive experiments, our ap-proach shows strong attacking ability in both the white-box and black-box setting.
1 code implementation • 6 Feb 2020 • Tao Bai, Jun Zhao, Jinlin Zhu, Shoudong Han, Jiefeng Chen, Bo Li, Alex Kot
Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs.
no code implementations • 27 Nov 2019 • Jun Zhao, Teng Wang, Tao Bai, Kwok-Yan Lam, Zhiying Xu, Shuyu Shi, Xuebin Ren, Xinyu Yang, Yang Liu, Han Yu
Although both classical Gaussian mechanisms [1, 2] assume $0 < \epsilon \leq 1$, our review finds that many studies in the literature have used the classical Gaussian mechanisms under values of $\epsilon$ and $\delta$ where the added noise amounts of [1, 2] do not achieve $(\epsilon,\delta)$-DP.
no code implementations • 24 Jun 2015 • Jingtuo Liu, Yafeng Deng, Tao Bai, Zhengping Wei, Chang Huang
Face Recognition has been studied for many decades.