Wei‐Shi Zheng

Improving Class Balancing at Both Feature Extractor and Classifier Head

2022 · 2022 IEEE International Conference on Multimedia and Expo (ICME)

Training data are often imbalanced across classes in practice, and such class imbalance issue often causes model predictions biased toward majority classes during inference. Different from existing solutions which employ various training strategies to alleviate …

Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor

2022 · arXiv (Cornell University)

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly in intelligent diagnosis …

FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detector

2024

Out-of-Distribution (OOD) detection is crucial when deploying machine learning models in open-world applications. The core challenge in OOD detection is mitigating the model's overconfidence on OOD data. While recent methods using auxiliary outlier datasets or …

Neural Prediction Errors as a Unified Cue for Abstract Visual Reasoning

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Humans exhibit remarkable abilities in recognizing relationships and performing complex reasoning. In contrast, deep neural networks have long been critiqued for their limitations in abstract visual reasoning (AVR), a key challenge in achieving artificial general …