Related papers: Sample-aware RandAugment: Search-free Automatic Da…

Despite the rapid growth in datasets for video activity, stable robust activity recognition with neural networks remains challenging. This is in large part due to the explosion of possible variation in video -- including lighting changes,…

The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search is the evaluation process for a particular augmentation…

Modern machine learning solutions require extensive data collection where labeling remains costly. To reduce this burden, open set active learning approaches aim to select informative samples from a large pool of unlabeled data that…

We propose an on-the-fly data augmentation method for automatic speech recognition (ASR) that uses alignment information to generate effective training samples. Our method, called Aligned Data Augmentation (ADA) for ASR, replaces…

This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks, including source-free domain…

The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel…

Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augmentation methods have led to further improvements on image…

Data augmentation has been widely used in low-resource NER tasks to tackle the problem of data sparsity. However, previous data augmentation methods have the disadvantages of disrupted syntactic structures, token-label mismatch, and…

Source-Free Unsupervised Domain Adaptation (SFUDA) has recently become a focus in the medical image domain adaptation, as it only utilizes the source model and does not require annotated target data. However, current SFUDA approaches cannot…

As an essential branch of recommender systems, sequential recommendation (SR) has received much attention due to its well-consistency with real-world situations. However, the widespread data sparsity issue limits the SR model's performance.…

State-of-the-art (SOTA) semi-supervised learning techniques, such as FixMatch and it's variants, have demonstrated impressive performance in classification tasks. However, these methods are not directly applicable to regression tasks. In…

Stain variations often decrease the generalization ability of deep learning based approaches in digital histopathology analysis. Two separate proposals, namely stain normalization (SN) and stain augmentation (SA), have been spotlighted to…

We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data…

Regularized linear discriminant analysis (RLDA) is a widely used tool for classification and dimensionality reduction, but its performance in high-dimensional scenarios is inconsistent. Existing theoretical analyses of RLDA often lack clear…

Conventional Low-Rank Adaptation (LoRA) methods employ a fixed rank, imposing uniform adaptation across transformer layers and attention heads despite their heterogeneous learning dynamics. This paper introduces Adaptive Rank Dynamic LoRA…

Designing reinforcement learning curricula for agile robots traditionally requires extensive manual tuning of reward functions, environment randomizations, and training configurations. We introduce AURA (Autonomous Upskilling with…

In recent years, deep learning has achieved remarkable achievements in many fields, including computer vision, natural language processing, speech recognition and others. Adequate training data is the key to ensure the effectiveness of the…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all…

Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…