1 code implementation • 14 Mar 2024 • Zhuo Zhi, Ziquan Liu, Moe Elbadawi, Adam Daneshmend, Mine Orlu, Abdul Basit, Andreas Demosthenous, Miguel Rodrigues
The proposed data-dependent framework exhibits a higher degree of sample efficiency and is empirically demonstrated to enhance the classification model's performance on both full- and missing-modality data in the low-data regime across various multimodal learning tasks.
no code implementations • 4 Feb 2024 • Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel Rodrigues
Our paper offers a new approach to certify the performance of machine learning models in the presence of adversarial attacks with population level risk guarantees.
no code implementations • 25 Aug 2023 • Reem I. Masoud, Ziquan Liu, Martin Ferianc, Philip Treleaven, Miguel Rodrigues
The deployment of large language models (LLMs) raises concerns regarding their cultural misalignment and potential ramifications on individuals from various cultural norms.
1 code implementation • CVPR 2023 • Qiangqiang Wu, Tianyu Yang, Ziquan Liu, Baoyuan Wu, Ying Shan, Antoni B. Chan
However, we find that this simple baseline heavily relies on spatial cues while ignoring temporal relations for frame reconstruction, thus leading to sub-optimal temporal matching representations for VOT and VOS.
Ranked #1 on Visual Object Tracking on TrackingNet (AUC metric)
1 code implementation • CVPR 2023 • Ziquan Liu, Yi Xu, Xiangyang Ji, Antoni B. Chan
To better exploit the potential of pre-trained models in adversarial robustness, this paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks.
no code implementations • 11 Oct 2022 • Ziquan Liu, Antoni B. Chan
Our empirical study on feedforward DNNs demonstrates that the proposed effective margin regularization (EMR) learns large effective margins and boosts the adversarial robustness in both standard and adversarial training.
no code implementations • 25 May 2022 • Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Xiangyang Ji, Antoni B. Chan
With our empirical result obtained from 1, 330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e. g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts.
no code implementations • 24 Nov 2021 • Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Xiangyang Ji, Antoni Chan, Rong Jin
The generalization result of using pre-training data shows that the excess risk bound on a target task can be improved when the appropriate pre-training data is included in fine-tuning.
no code implementations • CVPR 2021 • Jia Wan, Ziquan Liu, Antoni B. Chan
In this paper, we investigate learning the density map representation through an unbalanced optimal transport problem, and propose a generalized loss function to learn density maps for crowd counting and localization.
no code implementations • 6 Feb 2021 • Ziquan Liu, Yufei Cui, Jia Wan, Yu Mao, Antoni B. Chan
On the one hand, when the non-adaptive learning rate e. g. SGD with momentum is used, the effective learning rate continues to increase even after the initial training stage, which leads to an overfitting effect in many neural architectures.
1 code implementation • CVPR 2021 • Yufei Cui, Yu Mao, Ziquan Liu, Qiao Li, Antoni B. Chan, Xue Liu, Tei-Wei Kuo, Chun Jason Xue
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training.
no code implementations • ICML Workshop AML 2021 • Ziquan Liu, Yufei Cui, Antoni B. Chan
The derived regularizer is an upper bound for the input gradient of the network so minimizing the improved regularizer also benefits the adversarial robustness.