no code implementations • 13 Oct 2023 • Yizhou Yan, Xinyu Tang, Chao Huang, Ming Tang
The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising.
no code implementations • 11 Mar 2023 • Yu Wang, Lei Cao, Yizhou Yan, Samuel Madden
Moreover, to effectively handle high dimensional, highly complex data sets which are hard to summarize with simple rules, we propose a localized STAIR approach, called L-STAIR.
no code implementations • 25 Sep 2019 • Lei Cao, Yizhou Yan, Samuel Madden, Elke Rundensteiner
Unfortunately, although the strong generalization ability of existing CNNs ensures their accuracy when classifying known objects, it also causes them to often assign an unknown to a target class with high confidence.
no code implementations • 25 Sep 2019 • Yizhou Yan, Lei Cao, Samuel Madden, Elke Rundensteiner
Although the state-of-the-art object detection methods are successful in detecting and classifying objects by leveraging deep convolutional neural networks (CNNs), these methods overlook the semantic context which implies the probabilities that different classes of objects occur jointly.
no code implementations • ICLR 2019 • Lei Cao, Yizhou Yan, Samuel Madden, Elke Rundensteiner
Modern applications from Autonomous Vehicles to Video Surveillance generate massive amounts of image data.