24 citations · 26 across the 4 of their papers we have counts for
4 papers · 1 filter
Tackling Noisy Labels with Network Parameter Additive Decomposition
Jingyi Wang, Xiaobo Xia, Long Lan +5
Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows…
SODA: Robust Training of Test-Time Data Adaptors
Zige Wang, Yonggang Zhang, Zhen Fang +3
Adapting models deployed to test distributions can mitigate the performance degradation caused by distribution shifts. However, privacy concerns may render model parameters inacces…
Towards Radar Emitter Recognition in Changing Environments with Domain Generalization
Honglin Wu, Xueqiong Li, Long Lan +2
Analyzing radar signals from complex Electronic Warfare (EW) environment is a non-trivial task.However, in the real world, the changing EW environment results in inconsistent signa…
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
Xiong Peng, Feng Liu, Jingfen Zhang +4
Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training dat…