62 citations · 250 across the 38 of their papers we have counts for
41 papers
RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias
Hao Cheng, Jinhao Duan, Hui Li +6
Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP). Compared with…
Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Network
Hao Cheng, Jiahang Cao, Erjia Xiao +2
Deploying energy-efficient deep learning algorithms on computational-limited devices, such as robots, is still a pressing issue for real-world applications. Spiking Neural Networks…
Tracing the Influence of Predecessors on Trajectory Prediction
Mengmeng Liu, Hao Cheng, Michael Ying Yang
In real-world traffic scenarios, agents such as pedestrians and car drivers often observe neighboring agents who exhibit similar behavior as examples and then mimic their actions t…
An End-to-End Framework of Road User Detection, Tracking, and Prediction from Monocular Images
Hao Cheng, Mengmeng Liu, Lin Chen
Perception that involves multi-object detection and tracking, and trajectory prediction are two major tasks of autonomous driving. However, they are currently mostly studied separa…
LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels
Mingcai Chen, Yuntao Du, Wei Tang +4
In real-world applications, perfect labels are rarely available, making it challenging to develop robust machine learning algorithms that can handle noisy labels. Recent methods ha…
Lattice-Aided Extraction of Spread-Spectrum Hidden Data
Fan Yang, Shanxiang Lyu, Hao Cheng +2
This paper discusses the problem of extracting spread spectrum hidden data from the perspective of lattice decoding. Since the conventional blind extraction scheme multi-carrier it…
Evaluating the Efficacy of Length-Controllable Machine Translation
Hao Cheng, Meng Zhang, Weixuan Wang +3
Length-controllable machine translation is a type of constrained translation. It aims to contain the original meaning as much as possible while controlling the length of the transl…
End-to-end Training and Decoding for Pivot-based Cascaded Translation Model
Hao Cheng, Meng Zhang, Liangyou Li +2
Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and pivot-target, are trained ind…
Is Silent eHMI Enough? A Passenger-Centric Study on Effective eHMI for Autonomous Personal Mobility Vehicles in the Field
Hailong Liu, Yang Li, Zhe Zeng +3
Autonomous Personal Mobility Vehicle (APMV) is a miniaturized autonomous vehicle designed to provide short-distance mobility to everyone in pedestrian-rich environments. By the cha…
LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints
Mengmeng Liu, Hao Cheng, Lin Chen +5
Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints. Existing methods typically rely on…
ForceFormer: Exploring Social Force and Transformer for Pedestrian Trajectory Prediction
Weicheng Zhang, Hao Cheng, Fatema T. Johora +1
Predicting trajectories of pedestrians based on goal information in highly interactive scenes is a crucial step toward Intelligent Transportation Systems and Autonomous Driving. Th…
ShadowFormer: Global Context Helps Image Shadow Removal
Lanqing Guo, Siyu Huang, Ding Liu +2
Recent deep learning methods have achieved promising results in image shadow removal. However, most of the existing approaches focus on working locally within shadow and non-shadow…
Generating Evidential BEV Maps in Continuous Driving Space
Yunshuang Yuan, Hao Cheng, Michael Ying Yang +1
Safety is critical for autonomous driving, and one aspect of improving safety is to accurately capture the uncertainties of the perception system, especially knowing the unknown. D…
GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model
Hao Cheng, Mengmeng Liu, Lin Chen +3
Trajectory prediction has been a long-standing problem in intelligent systems like autonomous driving and robot navigation. Models trained on large-scale benchmarks have made signi…
INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Zeqiu Wu, Ryu Parish, Hao Cheng +4
In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types acco…
READ: Aggregating Reconstruction Error into Out-of-distribution Detection
Wenyu Jiang, Yuxin Ge, Hao Cheng +3
Detecting out-of-distribution (OOD) samples is crucial to the safe deployment of a classifier in the real world. However, deep neural networks are known to be overconfident for abn…
Identifiability of Label Noise Transition Matrix
Yang Liu, Hao Cheng, Kun Zhang
The noise transition matrix plays a central role in the problem of learning with noisy labels. Among many other reasons, a large number of existing solutions rely on access to it.…
Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise
Mingcai Chen, Hao Cheng, Yuntao Du +3
Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervis…
RMNet: Equivalently Removing Residual Connection from Networks
Fanxu Meng, Hao Cheng, Jiaxin Zhuang +2
Although residual connection enables training very deep neural networks, it is not friendly for online inference due to its multi-branch topology. This encourages many researchers…
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Jiaheng Wei, Zhaowei Zhu, Hao Cheng +3
Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic noise, though has clean structures which greatly enabled statistical analyses, of…
Mitigating Memorization of Noisy Labels via Regularization between Representations
Hao Cheng, Zhaowei Zhu, Xing Sun +1
Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs).…
Disentangled Feature Representation for Few-shot Image Classification
Hao Cheng, Yufei Wang, Haoliang Li +2
Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for f…
Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving
Yunshuang Yuan, Hao Cheng, Monika Sester
Sharing collective perception messages (CPM) between vehicles is investigated to decrease occlusions so as to improve the perception accuracy and safety of autonomous driving. Howe…
Bayesian Analysis of Multivariate Matched Proportions with Sparse Response
Mark J. Meyer, Haobo Cheng, Katherine Hobbs Knutson
Multivariate matched proportions (MMP) data appears in a variety of contexts including post-market surveillance of adverse events in pharmaceuticals, disease classification, and ag…