5 code implementations • 28 Jan 2022 • Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura, Zhiding Yu, Chaowei Xiao, Z. Morley Mao
Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications.
Ranked #1 on 3D Point Cloud Data Augmentation on ModelNet40-C
3D Point Cloud Classification 3D Point Cloud Data Augmentation +2
1 code implementation • CVPR 2022 • Qingzhao Zhang, Shengtuo Hu, Jiachen Sun, Qi Alfred Chen, Z. Morley Mao
Trajectory prediction is a critical component for autonomous vehicles (AVs) to perform safe planning and navigation.
1 code implementation • 22 Sep 2023 • Qingzhao Zhang, Shuowei Jin, Ruiyang Zhu, Jiachen Sun, Xumiao Zhang, Qi Alfred Chen, Z. Morley Mao
To understand the impact of the vulnerability, we break the ground by proposing various real-time data fabrication attacks in which the attacker delivers crafted malicious data to victims in order to perturb their perception results, leading to hard brakes or increased collision risks.
no code implementations • 30 Jun 2020 • Jiachen Sun, Yulong Cao, Qi Alfred Chen, Z. Morley Mao
In this work, we perform the first study to explore the general vulnerability of current LiDAR-based perception architectures and discover that the ignored occlusion patterns in LiDAR point clouds make self-driving cars vulnerable to spoofing attacks.
no code implementations • 24 Nov 2020 • Jiachen Sun, Karl Koenig, Yulong Cao, Qi Alfred Chen, Z. Morley Mao
Since adversarial training (AT) is believed as the most robust defense, we present the first in-depth study showing how AT behaves in point cloud classification and identify that the required symmetric function (pooling operation) is paramount to the 3D model's robustness under AT.
no code implementations • NeurIPS 2021 • Jiachen Sun, Yulong Cao, Christopher B. Choy, Zhiding Yu, Anima Anandkumar, Zhuoqing Morley Mao, Chaowei Xiao
In this paper, we systematically study the impact of various self-supervised learning proxy tasks on different architectures and threat models for 3D point clouds with adversarial training.
no code implementations • 28 Sep 2020 • Jiachen Sun, Karl Koenig, Yulong Cao, Qi Alfred Chen, Zhuoqing Mao
Since adversarial training (AT) is believed to be the most effective defense, we present the first in-depth study showing how AT behaves in point cloud classification and identify that the required symmetric function (pooling operation) is paramount to the model's robustness under AT.
no code implementations • 1 Dec 2021 • Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao
To alleviate this issue, we propose a novel data augmentation scheme, FourierMix, that produces augmentations to improve the spectral coverage of the training data.
no code implementations • 14 Jul 2022 • Mingyang Yi, Ruoyu Wang, Jiachen Sun, Zhenguo Li, Zhi-Ming Ma
The correlation shift is caused by the spurious attributes that correlate to the class label, as the correlation between them may vary in training and test data.
no code implementations • 21 Aug 2022 • Jiachen Sun, Weili Nie, Zhiding Yu, Z. Morley Mao, Chaowei Xiao
3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging.
no code implementations • IEEE Transactions on Network Science and Engineering 2022 • Jiachen Sun, Ning Ge, Xu Chen, Wei Feng, Jianhua Lu
This screening algorithm is customer-oriented and offers personalized commodities by preventing unqualified sellers from participating in the transaction.
no code implementations • 1 Jun 2023 • Jiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Z. Morley Mao, Chaowei Xiao
CALICO's efficacy is substantiated by extensive evaluations on 3D object detection and BEV map segmentation tasks, where it delivers significant performance improvements.
no code implementations • 26 Sep 2023 • Jiachen Sun, Mark Ibrahim, Melissa Hall, Ivan Evtimov, Z. Morley Mao, Cristian Canton Ferrer, Caner Hazirbas
Inspired by the success of textual prompting, several studies have investigated the efficacy of visual prompt tuning.
1 code implementation • 5 Oct 2023 • Zhuoyuan Wu, Jiachen Sun, Chaowei Xiao
In this study, we harness the inherent set property of point cloud data to introduce a novel critical subset identification (CSI) method, aiming to bolster recognition robustness in the face of data corruption.
no code implementations • 11 Oct 2023 • Haizhong Zheng, Jiachen Sun, Shutong Wu, Bhavya Kailkhura, Zhuoqing Mao, Chaowei Xiao, Atul Prakash
In this paper, we recognize that images share common features in a hierarchical way due to the inherent hierarchical structure of the classification system, which is overlooked by current data parameterization methods.
no code implementations • 1 Dec 2023 • Yingzi Ma, Yulong Cao, Jiachen Sun, Marco Pavone, Chaowei Xiao
The quest for fully autonomous vehicles (AVs) capable of navigating complex real-world scenarios with human-like understanding and responsiveness.