Related papers: Adversarial Auto-Augment with Label Preservation: …

Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment…

Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…

Data scarcity is a problem that occurs in languages and tasks where we do not have large amounts of labeled data but want to use state-of-the-art models. Such models are often deep learning models that require a significant amount of data…

Due to the limited availability of medical data, deep learning approaches for medical image analysis tend to generalise poorly to unseen data. Augmenting data during training with random transformations has been shown to help and became a…

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are…

Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed…

In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…

Deep Neural Networks (DNNs) show a significant impact on medical imaging. One significant problem with adopting DNNs for skin cancer classification is that the class frequencies in the existing datasets are imbalanced. This problem hinders…

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…

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks. However, the quality of the automatically generated…

Data augmentation has always been an effective way to overcome overfitting issue when the dataset is small. There are already lots of augmentation operations such as horizontal flip, random crop or even Mixup. However, unlike image…

A command-following robot that serves people in everyday life must continually improve itself in deployment domains with minimal help from its end users, instead of engineers. Previous methods are either difficult to continuously improve…

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While…

Self-supervised graph representation learning (SSGRL) is a representation learning paradigm used to reduce or avoid manual labeling. An essential part of SSGRL is graph data augmentation. Existing methods usually rely on heuristics commonly…

In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

Supervised learning can improve the design of state-of-the-art solvers for combinatorial problems, but labelling large numbers of combinatorial instances is often impractical due to exponential worst-case complexity. Inspired by the recent…

Source-free domain-adaptive object detection is an interesting but scarcely addressed topic. It aims at adapting a source-pretrained detector to a distinct target domain without resorting to source data during adaptation. So far, there is…

Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and expensive to acquire. In face recognition, large pose and…