Related papers: Learning Instance-Specific Augmentations by Captur…

This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space. Motivated by the positive concentrated and negative separated properties…

The growing use of virtual autonomous agents in applications like games and entertainment demands better control policies for natural-looking movements and actions. Unlike the conventional approach of hard-coding motion routines, we propose…

This article presents an efficient way to produce feature-rich, high-dimensionality embedding spaces from real-life images. The features produced are designed to be independent from augmentations used in real-life cases which appear on…

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor…

Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms…

Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the…

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this…

Machine Unlearning (MU) aims to remove the influence of specific data from a trained model while preserving its performance on the remaining data. Although a few works suggest connections between memorisation and augmentation, the role of…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

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…

Indoor localization has been a hot area of research over the past two decades. Since its advent, it has been steadily utilizing the emerging technologies to improve accuracy, and machine learning has been at the heart of that. Machine…

This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At…

In the realm of machine learning, the study of anomaly detection and localization within image data has gained substantial traction, particularly for practical applications such as industrial defect detection. While the majority of existing…

Data augmentation is widely used in vision to introduce variation and mitigate overfitting, by enabling models to learn invariant properties. However, augmentation only indirectly captures these properties and does not explicitly constrain…

Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation. From domain adaptation perspective, the key challenge is to learn…

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by…

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches…

Recent advances in personalized image generation allow a pre-trained text-to-image model to learn a new concept from a set of images. However, existing personalization approaches usually require heavy test-time finetuning for each concept,…

Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high. Besides active learning, data augmentation is also an effective technique to enlarge…