no code implementations • 9 Dec 2023 • Bowen Sun, Shibao Zheng
The blooming diffusion probabilistic models (DPMs) have garnered significant interest due to their impressive performance and the elegant inspiration they draw from physics.
1 code implementation • 5 Dec 2023 • Zhuo Huang, Chang Liu, Yinpeng Dong, Hang Su, Shibao Zheng, Tongliang Liu
Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed.
no code implementations • 3 Dec 2023 • Bowen Sun, Shibao Zheng
In this context, face recognition through textual description presents a unique and promising solution that not only transcends the limitations from application scenarios but also expands the potential for research in the field of cross-modal face recognition.
no code implementations • 19 Jul 2023 • Zhigang Chang, Weitai Hu, Qing Yang, Shibao Zheng
In dyadic speaker-listener interactions, the listener's head reactions along with the speaker's head movements, constitute an important non-verbal semantic expression together.
1 code implementation • CVPR 2023 • Zijian Zhu, Yichi Zhang, Hai Chen, Yinpeng Dong, Shu Zhao, Wenbo Ding, Jiachen Zhong, Shibao Zheng
However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems.
no code implementations • 1 Mar 2023 • Yichi Zhang, Zijian Zhu, Hang Su, Jun Zhu, Shibao Zheng, Yuan He, Hui Xue
In this paper, we propose Adversarial Semantic Contour (ASC), an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour.
no code implementations • 28 Feb 2023 • Chang Liu, Wenzhao Xiang, Yuan He, Hui Xue, Shibao Zheng, Hang Su
To address this issue, we proposed a novel method of Augmenting data with Adversarial examples via a Wavelet module (AdvWavAug), an on-manifold adversarial data augmentation technique that is simple to implement.
no code implementations • 28 Feb 2023 • Chang Liu, Yinpeng Dong, Wenzhao Xiang, Xiao Yang, Hang Su, Jun Zhu, Yuefeng Chen, Yuan He, Hui Xue, Shibao Zheng
In our benchmark, we evaluate the robustness of 55 typical deep learning models on ImageNet with diverse architectures (e. g., CNNs, Transformers) and learning algorithms (e. g., normal supervised training, pre-training, adversarial training) under numerous adversarial attacks and out-of-distribution (OOD) datasets.
no code implementations • 10 Dec 2021 • Zhigang Chang, Zhao Yang, Yongbiao Chen, Qin Zhou, Shibao Zheng
Validations on the gait recognition metric CASIA-B dataset further demonstrated the capability of our hybrid model.
no code implementations • 1 Dec 2021 • Chuang Liu, Hua Yang, Qin Zhou, Shibao Zheng
One major challenge comes from the imbalanced long-tail person identity distributions, which prevents the one-step person search model from learning discriminative person features for the final re-identification.
no code implementations • 30 Sep 2021 • Zijian Zhu, Hang Su, Chang Liu, Wenzhao Xiang, Shibao Zheng
Fortunately, most existing adversarial patches can be outwitted, disabled and rejected by a simple classification network called an adversarial patch detector, which distinguishes adversarial patches from original images.
no code implementations • 13 Sep 2021 • Wenzhao Xiang, Hang Su, Chang Liu, Yandong Guo, Shibao Zheng
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities.
no code implementations • ICML Workshop AML 2021 • Wenzhao Xiang, Chang Liu, Shibao Zheng
Traditional adversarial examples are typically generated by adding perturbation noise to the input image within a small matrix norm.
no code implementations • 24 Aug 2021 • Chuang Liu, Hua Yang, Qin Zhou, Shibao Zheng
In the proposed TDN, for better knowledge transfer from the Re-ID teacher model to the one-step person search model, we design a strong one-step person search base framework by partially disentangling the two subtasks.
no code implementations • 17 Nov 2019 • Zhigang Chang, Qin Zhou, Mingyang Yu, Shibao Zheng, Hua Yang, Tai-Pang Wu
To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obtain discriminative feature embedding.
1 code implementation • NeurIPS 2019 • Xinzhe Li, Qianru Sun, Yaoyao Liu, Shibao Zheng, Qin Zhou, Tat-Seng Chua, Bernt Schiele
On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning.
no code implementations • 15 May 2018 • Qin Zhou, Heng Fan, Hua Yang, Hang Su, Shibao Zheng, Shuang Wu, Haibin Ling
To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID.
no code implementations • 1 Apr 2018 • Qin Zhou, Heng Fan, Shibao Zheng, Hang Su, Xinzhe Li, Shuang Wu, Haibin Ling
In this paper, we propose a graph correspondence transfer (GCT) approach for person re-identification.
no code implementations • 22 Mar 2018 • Zhigang Chang, Qin Zhou, Heng Fan, Hang Su, Hua Yang, Shibao Zheng, Haibin Ling
Meanwhile, a weighting scheme is applied on the bilinear coding to adaptively adjust the weights of local features at different locations based on their importance in recognition, further improving the discriminability of feature aggregation.