To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Supervised learning algorithms have shown limited use in the field of anomaly detection due
to the unpredictability and difficulty in acquiring abnormal samples. In recent years …

In this paper, we address the few-shot classification task from a new perspective of optimal
matching between image regions. We adopt the Earth Mover's Distance (EMD) as a metric to …

Learning from a limited number of samples is challenging since the learned model can
easily become overfitted based on the biased distribution formed by only a few training …

Image-to-image translation (I2I) aims to transfer images from a source domain to a target
domain while preserving the content representations. I2I has drawn increasing attention and …

Machine learning has been highly successful in data-intensive applications but is often
hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to …

Several recent works have shown how highly realistic human head images can be obtained
by training convolutional neural networks to generate them. In order to create a personalized …

Meta-learning has been proposed as a framework to address the challenging few-shot
learning setting. The key idea is to leverage a large number of similar few-shot tasks in order …

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL)
methods: the pre-trained knowledge is indeed a confounder that limits the performance. This …

We propose a novel few-shot action recognition framework, STRM, which enhances class-
specific feature discriminability while simultaneously learning higher-order temporal …