Graph Neural Networks (GNNs) have been shown to possess strong represent...
Graph Neural Networks (GNNs) require a large number of labeled graph sam...
Cross-domain few-shot classification induces a much more challenging pro...
New objects are continuously emerging in the dynamically changing world ...
Medical image segmentation methods typically rely on numerous dense anno...
Unsupervised domain adaptation reduces the reliance on data annotation i...
As safety violations can lead to severe consequences in real-world robot...
Medical image annotation typically requires expert knowledge and hence i...
Classical machine learners are designed only to tackle one task without
...
Graph Neural Networks (GNNs) require a relatively large number of labele...
The generalization gap in reinforcement learning (RL) has been a signifi...
Recent domain adaptation methods have demonstrated impressive improvemen...
Domain adaptation, as a task of reducing the annotation cost in a target...
Recently the problem of cross-domain object detection has started drawin...
Deep learning models are difficult to obtain good performance when data ...
Deep learning models often require much annotated data to obtain good
pe...
Partial label (PL) learning tackles the problem where each training inst...
Domain adaptation aims to exploit a label-rich source domain for learnin...
Early Unsupervised Domain Adaptation (UDA) methods have mostly assumed t...
In this paper, we propose a novel end-to-end unsupervised deep domain
ad...
To date, most state-of-the-art sequence modelling architectures use atte...
In this paper we propose a novel dual adversarial co-learning approach f...
Automatic question generation is an important problem in natural languag...
In this paper, we propose a novel deep multi-level attention model to ad...
Partial multi-label learning (PML), which tackles the problem of learnin...
Object detection, as of one the most fundamental and challenging problem...
Zero-shot learning transfers knowledge from seen classes to novel unseen...
Despite the advancement of supervised image recognition algorithms, thei...
Despite the breakthroughs achieved by deep learning models in convention...
We consider the problem of learning Bayesian network classifiers that
ma...
We present a new approach to learning the structure and parameters of a
...