Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.
In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples.
In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction.
To tackle this issue, we propose a simple yet effective meta-learning framework for metricbased approaches, which we refer to as learning to generalize (L2G), that explicitly constrains the learning on a sampled classification task to reduce the classification error on a randomly sampled unseen classification task with a bilevel optimization scheme.
Most existing relation extraction models assume a fixed set of relations and are unable to adapt to exploit newly available supervision data to extract new relations.
A solution to mitigate the small training set issue is to train a denoising model with pairs of clean and synthesized noisy signals, produced from empirical noise priors; and finally only fine-tune on the available small training set.
Particularly, MetaL-TDVS aims to excavate the latent mechanism for summarizing video by reformulating video summarization as a meta learning problem and promote generalization ability of the trained model.
In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations.