Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deeplearning classifiers. In this work we propose balancing GANs (BAGANs) as an augmentation tool to restore balance in imbalanced datasets. This is challenging because the few minority-class images may not be enough to train a GAN. We overcome this issue by including during training all a...

Arnaud Doucet EE Engineering University of Melbourne Parkville, Victoria 3052 Australia [email protected] In this paper, we extend the Rao-Blackwellised particle filtering method to more complex hybrid models consisting of Gaussian latent variables and discrete observations. This is accomplished by augmenting the models with artificial variables that enable us to apply Rao-Blackwellisation. Ot...

Relational topic models have shown promise on analyzing document network structures and discovering latent topic representations. This paper presents three extensions: 1) unlike the common link likelihood with a diagonal weight matrix that allows the-same-topic interactions only, we generalize it to use a full weight matrix that captures all pairwise topic interactions and is applicable to asym...

The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose. This architecture exploits a parametrization of the pose manifold in terms of pose and appearance. This leads to a deep encoder/decoder network architecture, where the encode...

This paper presents a latent variable representation of regularized support vector machines (SVM’s) that enables EM, ECME or MCMC algorithms to provide parameter estimates. We verify our representation by demonstrating that minimizing the SVM optimality criterion together with the parameter regularization penalty is equivalent to finding the mode of a mean-variance mixture of normals pseudo-pos...

The original goal of this project was to investigate the extent to which data augmentation schemes based on semi-supervised learning algorithms can improve classification accuracy in supervised learning problems. The objectives included determining the appropriate algorithms, customising them for the purposes of this project and providing their Matlab implementations. These algorithms were to b...

Recently there has been interest in the approaches for training speech recognition systems for languages with limited resources. Under the IARPA Babel program such resources have been provided for a range of languages to support this research area. This paper examines a particular form of approach, data augmentation, that can be applied to these situations. Data augmentation schemes aim to incr...

Large linked data repositories have been built by leveraging semi-structured data in Wikipedia (e.g., DBpedia) and through extracting information from natural language text (e.g., YAGO). However, the Web contains many other vast sources of linked data, such as structured HTML tables and spreadsheets. Often, the semantics in such tables is hidden, preventing one from extracting triples from them...

Due to catastrophic forgetting, deep learning remains highly inappropriate when facing incremental learning of new classes and examples over time. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA combines transfer learning from a pre-trained Deep Neural Network (DNN) as feature extractor, a Nearest Class Mean (NCM) inspired classifier and m...

The motivations of multiple kernel learning (MKL) approach are to increase kernel expressiveness capacity and to avoid the expensive grid search over a wide spectrum of kernels. A large amount of work has been proposed to improve the MKL in terms of the computational cost and the sparsity of the solution. However, these studies still either require an expensive grid search on the model paramete...