Few-shot hyperspectral image (HSI) classification poses challenges due to sample selection
bias in few-shot scenarios, potentially leading to incorrect statistical associations between …

Few-shot learning aims to transfer the knowledge learned from seen categories to unseen
categories with a few references. It is also an essential challenge to bridge the gap between …

Meta-learning aims to leverage prior knowledge from related tasks to enable a base learner
to quickly adapt to new tasks with limited labeled samples. However, traditional meta …

Gait recognition is a promising biometric technology that aims to identify the target subject
via walking pattern. Most existing appearance-based methods focus on learning …

Deep reinforcement learning (DRL) has emerged as an efficient approach for motion
planning in mobile robot systems. It leverages the offline training process to enhance real …

Abstract Representation learning assumes that real-world data is generated by a few
semantically meaningful generative factors (ie, sources of variation) and aims to discover …

In recent years, several few-shot learning (FSL) approaches for industrial equipment fault
diagnosis have emerged to tackle the challenges posed by small fault diagnosis datasets …

Abstract Few-Shot Learning (FSL) aims to train a model that can generalize to recognize
new classes, with each new class having only very limited training samples. Since extracting …

Cross-domain hyperspectral image (HSI) classification can improve the model's
classification performance in the target domain by utilizing the rich knowledge from the …

Integrating deep learning and causal discovery has encouraged us to spot that learning
causal structures and representations in dialogue and video is full of challenges. We defined …