The remarkable performance of the Transformer architecture in natural language processing
has recently also triggered broad interest in Computer Vision. Among other merits …

In action recognition, although the combination of spatio-temporal videos and skeleton
features can improve the recognition performance, a separate model and balancing feature …

Recent advancements in large-scale Vision Transformers have made significant strides in
improving pre-trained models for medical image segmentation. However, these methods …

Neural networks (NNs) and decision trees (DTs) are both popular models of machine
learning, yet coming with mutually exclusive advantages and limitations. To bring the best of …

Fine-grained visual classification is a challenging task due to the high similarity between
categories and distinct differences among data within one single category. To address the …

Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up
studies due to its self-explanatory property for explainable artificial intelligence (XAI) …

Although purely transformer-based architectures pretrained on large datasets are introduced
as foundation models for general computer vision tasks, hybrid models that incorporate …

Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable
classification by associating predictions with a set of training prototypes, which we refer to as …

Prototypical part neural networks (ProtoPartNNs), namely ProtoPNet and its derivatives, are
an intrinsically interpretable approach to machine learning. Their prototype learning scheme …

The challenge of Fine-grained visual classification (FGVC) comes from the small variations
between classes and the large variations within classes. Inspired by the fact that identifying …