Related papers: Data Augmentation via Causal-Residual Bootstrappin…

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…

Cultural heritage applications and advanced machine learning models are creating a fruitful synergy to provide effective and accessible ways of interacting with artworks. Smart audio-guides, personalized art-related content and gamification…

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By…

We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression. Our data augmentation algorithm borrows from the literature on causality and extends the recently proposed Anchor regression (AR) method for data…

The era of big data has witnessed an increasing availability of observational data from mobile and social networking, online advertising, web mining, healthcare, education, public policy, marketing campaigns, and so on, which facilitates…

Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. Yet, there is little rigorous understanding of why and how various augmentations work. In this work, we consider a…

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…

State-of-the-art models for keyphrase generation require large amounts of training data to achieve good performance. However, obtaining keyphrase-labeled documents can be challenging and costly. To address this issue, we present a…

Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and…

Self-supervised representation learning is heavily dependent on data augmentations to specify the invariances encoded in representations. Previous work has shown that applying diverse data augmentations is crucial to downstream performance,…

In this paper, we reveal the two sides of data augmentation: enhancements in closed-set recognition correlate with a significant decrease in open-set recognition. Through empirical investigation, we find that multi-sample-based…

Learning recipe and food image representation in common embedding space is non-trivial but crucial for cross-modal recipe retrieval. In this paper, we propose a new perspective for this problem by utilizing foundation models for data…

With the latest advances in Deep Learning-based generative models, it has not taken long to take advantage of their remarkable performance in the area of time series. Deep neural networks used to work with time series heavily depend on the…

Perturbation experiments allow biologists to discover causal relationships between variables of interest, but the sparsity and high dimensionality of these data pose significant challenges for causal structure learning algorithms.…

Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models. However, in real life applications these models often encounter scenarios that are…

The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great…

Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is…

In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data…