Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

Despite its astounding success in learning deeper multi-dimensional data, the performance
of deep learning declines on new unseen tasks mainly due to its focus on same-distribution …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

Detecting rare objects from a few examples is an emerging problem. Prior works show meta-
learning is a promising approach. But, fine-tuning techniques have drawn scant attention …

Meta-learning has been the most common framework for few-shot learning in recent years. It
learns the model from collections of few-shot classification tasks, which is believed to have a …

Abstract Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel
compositional concepts based on learned concepts such as attribute-object combinations …

Multi-task learning is a very challenging problem in reinforcement learning. While training
multiple tasks jointly allow the policies to share parameters across different tasks, the …

Few-shot object detection (FSOD) aims to strengthen the performance of novel object
detection with few labeled samples. To alleviate the constraint of few samples, enhancing …

Visual attributes constitute a large portion of information contained in a scene. Objects can
be described using a wide variety of attributes which portray their visual appearance (color …

Few-shot classification aims to recognize unseen classes when presented with only a small
number of samples. We consider the problem of multi-domain few-shot image classification …