Continual learning aims to learn a sequence of tasks without forgetting the previously
learned knowledge. Although existing memory-based approaches can be easily deployed …

Recent video class-incremental learning usually excessively pursues the accuracy of the
newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old …

Rehearsal-based video incremental learning often employs knowledge distillation to
mitigate catastrophic forgetting of previously learned data. However, this method faces two …

Continual learning has recently attracted attention from the research community, as it aims to
solve long-standing limitations of classic supervised-trained models. However, most …

Object detection on datasets with imbalanced distributions (ie long‐tail distributions) dataset
is a significantly challenging task. Some re‐balancing solutions, such as re‐weighting and …

Despite the significant advances achieved in Artificial Neural Networks (ANNs), their design
process remains notoriously tedious, depending primarily on intuition, experience and trial …

Humans can effortlessly learn from a specific data distribution and generalize well to various
situations without excessive supervision. In contrast, deep learning models often struggle to …

In this dissertation, the design and fabrication of deep-ultraviolet photodetectors were
investigated based on gallium oxide and its alloys, through the heterogeneous integration …

Deep learning has made tremendous progress in the last decade due to the explosion of
training data and computational power. Through end-to-end training on a large dataset …