Humans possess an extraordinary ability to create and utilize tools. With the advent of
foundation models, artificial intelligence systems have the potential to be equally adept in …

Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training
paradigm, successfully introduces text supervision to vision models. It has shown promising …

Multi-instance learning (MIL) is an effective paradigm for whole-slide pathological images
(WSIs) classification to handle the gigapixel resolution and slide-level label. Prevailing MIL …

Abstract Weakly Supervised Semantic Segmentation (WSSS) aims to learn the concept of
segmentation using image-level class labels. Recent WSSS works have shown promising …

Abstract Traditional Unsupervised Domain Adaptation (UDA) leverages the labeled source
domain to tackle the learning tasks on the unlabeled target domain. It can be more …

Abstract Three-dimensional (3D) cross-modality cardiac image segmentation is critical for
cardiac disease diagnosis and treatment. However, it confronts the challenge of modality …

Weakly supervised object localization (WSOL) remains challenging when learning object
localization models from image category labels. Conventional methods that discriminatively …

Accurate extraction of rooftop photovoltaic from high-resolution remote sensing imagery is
pivotal for propelling green energy planning and development. Conventional deep learning …

Deep learning has seen rapid growth in recent years and achieved state-of-the-art
performance in a wide range of applications. However, training models typically requires …

Federated learning (FL) effectively mitigates the data silo challenge brought about by
policies and privacy concerns, implicitly harnessing more data for deep model training …