Related papers: Meta Approach to Data Augmentation Optimization
Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for…
Popular approaches for minimizing loss in data-driven learning often involve an abstraction or an explicit retention of the history of gradients for efficient parameter updates. The aggregated history of gradients nudges the parameter…
Data augmentation methods enrich datasets with augmented data to improve the performance of neural networks. Recently, automated data augmentation methods have emerged, which automatically design augmentation strategies. Existing work…
We present an automated data augmentation approach for image classification. We formulate the problem as Monte Carlo sampling where our goal is to approximate the optimal augmentation policies. We propose a particle filtering scheme for the…
Deep convolutional neural networks have achieved exceptional results on multiple detection and recognition tasks. However, the performance of such detectors are often evaluated in public benchmarks under constrained and non-realistic…
Pre-training (PT) followed by fine-tuning (FT) is an effective method for training neural networks, and has led to significant performance improvements in many domains. PT can incorporate various design choices such as task and data…
Deep learning (DL) algorithms have shown significant performance in various computer vision tasks. However, having limited labelled data lead to a network overfitting problem, where network performance is bad on unseen data as compared to…
Augmenting training datasets has been shown to improve the learning effectiveness for several computer vision tasks. A good augmentation produces an augmented dataset that adds variability while retaining the statistical properties of the…
Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies in the image classification domain. However, two key points…
The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…
While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked…
Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample…
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…
Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment…
Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms…
Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…
Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…
While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the…
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…
Current methods for low- and few-shot object detection have primarily focused on enhancing model performance for detecting objects. One common approach to achieve this is by combining model finetuning with data augmentation strategies.…