Source Themes

We propose variational multi-task learning (VMTL), a general probabilistic inference framework in which we cast multi-task learning as a variational Bayesian inference problem.

We propose a model of semantic memory for WSD in a meta-learning setting.

We propose variational topic inference for automatic report generation.

In this paper, we address the challenges of domain shift and the uncertainty with a probabilistic framework based on variational Bayesian inference, by incorporating uncertainty into neural network weights.

We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific classifiers based on kernel ridge regression.

We propose MetaNorm, a simple yet effective meta-learning normalization approach that learns adaptive statistics for few-shot classification and domain generalization.

This paper strives for repetitive activity counting in videos. Different from existing works, which all analyze the visual video content only, we incorporate for the first time the corresponding sound into the repetition counting process.

This paper propose variational prototype inference to address few-shot semantic segmentation in a probabilistic framework.

We propose variational knowledge distillation (VKD), which is a new probabilistic inference framework for disease classification based on X-rays that lever- ages knowledge from EHRs.

Few-Shot Segmentation, Graph Attention, Democratic Attention Network, Multi-Scale Guidance