The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on
unsupervised pretraining methods shows superior transfer performance to their supervised …

Many state-of-the-art few-shot learners focus on developing effective training procedures for
feature representations, before using simple (eg, nearest centroid) classifiers. We take an …

We summarise experiments evaluating cross-domain few-shot learning (CDFSL) with
feature extractors trained on ImageNet. The work explores the transfer performance of …

The opening of this chapter introduces the techniques for the design and training of neural
networks that will be addressed in this thesis. We then highlight the key challenges in the …

Laboratory work is a unique aspect of science education and an important component of the
curriculum in tertiary chemistry education. Practitioners and researchers have described the …

Deep learning models need large amounts of data for training. In video recognition and
classification, significant advances were achieved with the introduction of new large …

Neural networks show promise in modelling infrared (IR) spectroscopic data, but many of the
proposed solutions in the literature are either Multilayer Perceptrons with a single hidden …