Data labeling is a critical and costly process, thus accessing large amounts of labeled data is not always feasible. Transfer Learning (TL) and Semi-Supervised Learning (SSL) are two promising approaches to leverage both labeled and unlabeled samples. In this work, we first study TL methods based on unsupervised pre-training strategies with Autoencoder (AE) networks. Then, we focus on clustering in the Semi-Supervised scenario. Previous works introduced the β-VAE, an AE that learns a disentangled data representation from the unlabeled samples. We conduct an initial study of un- supervised pre-training with AEs to assess its impact on image classification tasks. We also design a new training method for the β-VAE based on cyclical annealing. ...
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remai...
In this work, we set the stage of a limited labelling budget and propose using a sample selector net...
Image recognition is a subfield in computer vision, representing a set of methods for analyzing imag...
This master thesis tackles the problem of unsupervised learning of visual representations with deep ...
In this thesis, we address a number of challenges in cluster analysis. We begin by investigating one...
As the amount of data increases every year, the need for effective structuring of data is a growing ...
Clustering keywords is an important Natural Language Processing task that can be adopted by several ...
In this paper, we propose a clustering approach embedded in a deep convolutional auto-encoder (DCAE)...
Deep Learning has changed the way computer vision tasks are being solved in the current age. Deep Le...
Die Kombination von Deep Learning und Clustering, oft auch unter dem Namen Deep Clustering vereint, ...
Convolutional Neural Networks (CNNs) have been proved to deliver great results in the area of comput...
With the development of deep learning methods the requirement of having access to large amounts of d...
International audienceIn most real world clustering scenarios, experts generally dispose of limited ...
We propose a clustering approach embedded in deep convolutional auto-encoder. In contrast to convent...
Having a well representative and adequate amount of data samples plays an important role in the succ...
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remai...
In this work, we set the stage of a limited labelling budget and propose using a sample selector net...
Image recognition is a subfield in computer vision, representing a set of methods for analyzing imag...
This master thesis tackles the problem of unsupervised learning of visual representations with deep ...
In this thesis, we address a number of challenges in cluster analysis. We begin by investigating one...
As the amount of data increases every year, the need for effective structuring of data is a growing ...
Clustering keywords is an important Natural Language Processing task that can be adopted by several ...
In this paper, we propose a clustering approach embedded in a deep convolutional auto-encoder (DCAE)...
Deep Learning has changed the way computer vision tasks are being solved in the current age. Deep Le...
Die Kombination von Deep Learning und Clustering, oft auch unter dem Namen Deep Clustering vereint, ...
Convolutional Neural Networks (CNNs) have been proved to deliver great results in the area of comput...
With the development of deep learning methods the requirement of having access to large amounts of d...
International audienceIn most real world clustering scenarios, experts generally dispose of limited ...
We propose a clustering approach embedded in deep convolutional auto-encoder. In contrast to convent...
Having a well representative and adequate amount of data samples plays an important role in the succ...
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remai...
In this work, we set the stage of a limited labelling budget and propose using a sample selector net...
Image recognition is a subfield in computer vision, representing a set of methods for analyzing imag...