Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …

Early prediction of patient outcomes is important for targeting preventive care. This protocol
describes a practical workflow for developing deep-learning risk models that can predict …

In this paper, we tackle the problem of few-shot class incremental learning (FSCIL). FSCIL
aims to incrementally learn new classes with only a few samples in each class. Most existing …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Semantic segmentation is a challenging task in the absence of densely labelled data. Only
relying on class activation maps (CAM) with image-level labels provides deficient …

Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D
image. It is a highly challenging problem and remains open, especially when no extra …

In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for
several tasks. Joint training reduces computation costs and improves data efficiency; …

Extreme multi-label text classification~(XMC) seeks to find relevant labels from an extreme
large label collection for a given text input. Many real-world applications can be formulated …

Abstract Vision-Language Navigation (VLN) is a task where an agent learns to navigate
following a natural language instruction. The key to this task is to perceive both the visual …

Learning on graphs has attracted significant attention in the learning community due to
numerous real-world applications. In particular, graph neural networks (GNNs), which take …