Related papers: Dataset Augmentation in Feature Space
Deep learning-based models in medical imaging often struggle to generalize effectively to new scans due to data heterogeneity arising from differences in hardware, acquisition parameters, population, and artifacts. This limitation presents…
It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…
Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) aims to overcome the problem by leveraging multiple source…
In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this paper, we focus on condensing large training sets into…
In many classification problems, we want a classifier that is robust to a range of non-semantic transformations. For example, a human can identify a dog in a picture regardless of the orientation and pose in which it appears. There is…
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color…
We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are hand-designed and sample the space of possible augmented data points either at random, without knowing which augmented…
Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek…
In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not…
Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…
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…
Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features. It is crucial to address the curse of dimensionality, enhance model generalization, overcome data sparsity, and…
Data Augmentation (DA) is a technique to increase the quantity and diversity of the training data, and by that alleviate overfitting and improve generalisation. However, standard DA produces synthetic data for augmentation with limited…
Although larger datasets are crucial for training large deep models, the rapid growth of dataset size has brought a significant challenge in terms of considerable training costs, which even results in prohibitive computational expenses.…
Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
Deep networks for visual recognition are known to leverage "easy to recognise" portions of objects such as faces and distinctive texture patterns. The lack of a holistic understanding of objects may increase fragility and overfitting. In…
Data augmentation is a widely used and effective technique to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability when working with medical images, it is frequently…
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and…
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…