4 papers
Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition
Shuo Zhang, Chenqi Li, Tingting Zhu
Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning from classifier retraining, offe…
Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
Chenqi Li, Yu Liu, Shuo Zhang +2
Pretraining for electroencephalogram (EEG) foundation models has predominantly relied on self-supervised masked reconstruction, a paradigm largely adapted from and inspired by the…
BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals
Chenqi Li, Yu Liu, Timothy Denison +1
Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost…
AnchorInv: Few-Shot Class-Incremental Learning of Physiological Signals via Representation Space Guided Inversion
Chenqi Li, Boyan Gao, Gabriel Jones +2
Deep learning models have demonstrated exceptional performance in a variety of real-world applications. These successes are often attributed to strong base models that can generali…