Semi-Supervised Learning (SSL) leverages both labeled and unlabeled data...
In the domain of semi-supervised learning (SSL), the conventional approa...
In Active Learning (AL), a learner actively chooses which unlabeled exam...
Deep neural networks have incredible capacity and expressibility, and ca...
Deep active learning aims to reduce the annotation cost for deep neural
...
Investigating active learning, we focus on the relation between the numb...
The learning trajectories of linguistic phenomena provide insight into t...
Convolutional Neural networks of different architectures seem to learn t...
Overfit is a fundamental problem in machine learning in general, and in ...
Recently, Semi-Supervised Learning (SSL) has shown much promise in lever...
The generation of synthetic images is currently being dominated by Gener...
We revisit the long-standing problem of learning from small sample. In
r...
The clustering of unlabeled raw images is a daunting task, which has rec...
One of the unresolved questions in the context of deep learning is the
t...
Training neural networks is traditionally done by providing a sequence o...
Blurred Images Lead to Bad Local Minima...
Curriculum Learning - the idea of teaching by gradually exposing the lea...
Generative Adversarial Networks (GANs) have been shown to produce
realis...
Our first contribution in this paper is a theoretical investigation of
c...
The reliable measurement of confidence in classifiers' predictions is ve...
Deep learning has become the method of choice in many application domain...
We address the problem of novelty detection in multiclass scenarios wher...
Often in real-world datasets, especially in high dimensional data, some
...
The reliable detection of speed of moving vehicles is considered key to
...