activity
20172023
most citedSTFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks

71 citations · 131 across the 14 of their papers we have counts for

collaborators

18 papers

cs.CV2023

General-Purpose Multi-Modal OOD Detection Framework

Viet Duong, Qiong Wu, Zhengyi Zhou +5

Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) sy…

cs.LG2023★ 1 cited

Scalable Neural Symbolic Regression using Control Variables

Xieting Chu, Hongjue Zhao, Enze Xu +3

Symbolic regression (SR) is a powerful technique for discovering the analytical mathematical expression from data, finding various applications in natural sciences due to its good…

cs.LG2023★ 1 cited

Condensed Prototype Replay for Class Incremental Learning

Jiangtao Kong, Zhenyu Zong, Tianyi Zhou +1

Incremental learning (IL) suffers from catastrophic forgetting of old tasks when learning new tasks. This can be addressed by replaying previous tasks' data stored in a memory, whi…

cs.LG2023★ 3 cited

Balancing Privacy Protection and Interpretability in Federated Learning

Zhe Li, Honglong Chen, Zhichen Ni +1

Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby poten…

cs.SE2022★ 1 cited

Pre-Training Representations of Binary Code Using Contrastive Learning

Yifan Zhang, Chen Huang, Yueke Zhang +3

Binary code analysis and comprehension is critical to applications in reverse engineering and computer security tasks where source code is not available. Unfortunately, unlike sour…

cs.LG2022★ 1 cited

Phy-Taylor: Physics-Model-Based Deep Neural Networks

Yanbing Mao, Lui Sha, Huajie Shao +3

Purely data-driven deep neural networks (DNNs) applied to physical engineering systems can infer relations that violate physics laws, thus leading to unexpected consequences. To ad…