Search Results for author: Jihong Zhu

Found 8 papers, 4 papers with code

Boosting 3D Adversarial Attacks with Attacking On Frequency

no code implementations26 Jan 2022 Binbin Liu, Jinlai Zhang, Lyujie Chen, Jihong Zhu

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks.

3D Adversarial Attacks Beyond Point Cloud

1 code implementation25 Apr 2021 Jinlai Zhang, Lyujie Chen, Binbin Liu, Bo Ouyang, Qizhi Xie, Jihong Zhu, Weiming Li, Yanmei Meng

In order to take advantage of the most effective gradient-based attack, a differentiable sample module that back-propagate the gradient of point cloud to mesh is introduced.

Adversarial Attack

Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition

no code implementations13 Apr 2021 Yan Zhao, Weicong Chen, Xu Tan, Kai Huang, Jihong Zhu

The adaptive adjusting term is composed of two complementary factors: 1) quantity factor, which pays more attention to tail classes, and 2) difficulty factor, which adaptively pays more attention to hard instances in the training process.

General Classification Semantic Similarity +1

The art of defense: letting networks fool the attacker

1 code implementation7 Apr 2021 Jinlai Zhang, Binbin Liu, Lyvjie Chen, Bo Ouyang, Jihong Zhu, Minchi Kuang, Houqing Wang, Yanmei Meng

Some deep neural networks are invariant to some input transformations, such as Pointnet is permutation invariant to the input point cloud.

PointCutMix: Regularization Strategy for Point Cloud Classification

2 code implementations5 Jan 2021 Jinlai Zhang, Lyujie Chen, Bo Ouyang, Binbin Liu, Jihong Zhu, Yujing Chen, Yanmei Meng, Danfeng Wu

As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent.

3D Point Cloud Classification Classification +2

Robust Autonomous Landing of UAV in Non-Cooperative Environments based on Dynamic Time Camera-LiDAR Fusion

no code implementations27 Nov 2020 Lyujie Chen, Xiaming Yuan, Yao Xiao, Yiding Zhang, Jihong Zhu

We have conducted extensive autonomous landing experiments in a variety of familiar or completely unknown environments, verifying that our model can adaptively balance the accuracy and speed, and the UAV can robustly select a safe landing site.

Depth Completion

Cannot find the paper you are looking for? You can Submit a new open access paper.