Related papers: Learning Instance-Specific Augmentations by Captur…

Training a deep learning model to classify histopathological images is challenging, because of the color and shape variability of the cells and tissues, and the reduced amount of available data, which does not allow proper learning of those…

Data augmentation has proven to be effective in training neural networks. Recently, a method called RandAug was proposed, randomly selecting data augmentation techniques from a predefined search space. RandAug has demonstrated significant…

Although data augmentation is a powerful technique for improving the performance of image classification tasks, it is difficult to identify the best augmentation policy. The optimal augmentation policy, which is the latent variable, cannot…

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

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…

State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operations. The range of magnitudes of many augmentation operations…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

The quality of data augmentation serves as a critical determinant for the performance of contrastive learning in EEG tasks. Although this paradigm is promising for utilizing unlabeled data, static or random augmentation strategies often…

Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks. However, in most cases, data augmentation is randomly performed for each training sample with a certain probability, which might incur…

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes clustering and hash learning as special cases. Deep neural networks…

Handwritten text and scene text suffer from various shapes and distorted patterns. Thus training a robust recognition model requires a large amount of data to cover diversity as much as possible. In contrast to data collection and…

Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstream tasks of interest. However, different downstream tasks…

Aiming to produce sufficient and diverse training samples, data augmentation has been demonstrated for its effectiveness in training deep models. Regarding that the criterion of the best augmentation is challenging to define, we in this…

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…

Enhancing the generalization capability of robotic learning to enable robots to operate effectively in diverse, unseen scenes is a fundamental and challenging problem. Existing approaches often depend on pretraining with large-scale data…

Continuous reinforcement learning such as DDPG and A3C are widely used in robot control and autonomous driving. However, both methods have theoretical weaknesses. While DDPG cannot control noises in the control process, A3C does not satisfy…

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…

Medical image data are often limited due to the expensive acquisition and annotation process. Hence, training a deep-learning model with only raw data can easily lead to overfitting. One solution to this problem is to augment the raw data…

Time-series data augmentation mitigates the issue of insufficient training data for deep learning models. Yet, existing augmentation methods are mainly designed for classification, where class labels can be preserved even if augmentation…

Personalized and content-adaptive image enhancement can find many applications in the age of social media and mobile computing. This paper presents a relative-learning-based approach, which, unlike previous methods, does not require…