Related papers: ParticleAugment: Sampling-Based Data Augmentation

Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…

We consider a simple approach to solving assortment optimization under the random utility maximization model. The approach uses Monte-Carlo simulation to construct a ranking-based choice model that serves as a proxy for the true choice…

We present a new approach-the ALVar estimator-to estimation of asymptotic variance in sequential Monte Carlo methods, or, particle filters. The method, which adjusts adaptively the lag of the estimator proposed in [Olsson, J. and Douc, R.…

Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, however, requires large amounts of domain-specific visual…

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

Image segmentation is an important task in many medical applications. Methods based on convolutional neural networks attain state-of-the-art accuracy; however, they typically rely on supervised training with large labeled datasets. Labeling…

Image augmentation is a widely used technique to improve the performance of convolutional neural networks (CNNs). In common image shifting, cropping, flipping, shearing and rotating are used for augmentation. But there are more advanced…

In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning…

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Image enhancement is an important image processing technique that processes images suitably for a specific application e.g. image editing. The conventional solutions of image enhancement are grouped into two categories which are spatial…

Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen…

We consider Monte Carlo approximations to the maximum likelihood estimator in models with intractable norming constants. This paper deals with adaptive Monte Carlo algorithms, which adjust control parameters in the course of simulation. We…

Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection…

Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets. Consequently, a recent trend is to adopt AutoML technique…

There has been considerable interest in making Bayesian inference more scalable. In big data settings, most literature focuses on reducing the computing time per iteration, with less focused on reducing the number of iterations needed in…

Sequential Monte Carlo methods, also known as particle methods, are a widely used set of computational tools for inference in non-linear non-Gaussian state-space models. In many applications it may be necessary to compute the sensitivity,…

Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of…

High quality upsampling of sparse 3D point clouds is critically useful for a wide range of geometric operations such as reconstruction, rendering, meshing, and analysis. In this paper, we propose a data-driven algorithm that enables an…

Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…