Related papers: CAAP: Class-Dependent Automatic Data Augmentation …
Neural networks have become increasingly popular in the last few years as an effective tool for the task of image classification due to the impressive performance they have achieved on this task. In image classification tasks, it is common…
In many service systems, especially those in healthcare, customer waiting times can result in increased service requirements. Such service slowdowns can significantly impact system performance. Therefore, it is important to properly account…
Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…
We introduce Learning-Augmented Control (LAC), an approach that integrates untrusted machine learning predictions into the control of constrained, nonlinear dynamical systems. LAC is designed to achieve the "best-of-both-worlds" guarantees,…
Reliable machine learning and statistical analysis rely on diverse, well-distributed training data. However, real-world datasets are often limited in size and exhibit underrepresentation across key subpopulations, leading to biased…
Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision applications, where shifts in image background, style, and acquisition instruments always degrade model performance. Generic augmentations show…
This paper proposes an advantage estimation approach based on data augmentation for policy optimization. Unlike using data augmentation on the input to learn value and policy function as existing methods use, our method uses data…
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…
Recent advances in machine learning (ML) and computer vision tools have enabled applications in a wide variety of arenas such as financial analytics, medical diagnostics, and even within the Department of Defense. However, their widespread…
Artificial intelligence systems predominantly rely on static data distributions, making them ineffective in dynamic real-world environments, such as cybersecurity, autonomous transportation, or finance, where data shifts frequently.…
Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieved great success. However, existing automated DA methods…
Recently, deep neural networks have gained increasing popularity in the field of time series forecasting. A primary reason for their success is their ability to effectively capture complex temporal dynamics across multiple related time…
Class-Incremental Learning (CIL) requires models to continuously acquire new classes without forgetting previously learned ones. A dominant paradigm involves freezing a pre-trained model and training lightweight, task-specific adapters.…
Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…
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…
In the paper, we propose an adaptive data-driven model-based approach for filling the gaps in time series. The approach is based on the automated evolutionary identification of the optimal structure for a composite data-driven model. It…
Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…
Sequential recommender systems have recently achieved significant performance improvements with the exploitation of deep learning (DL) based methods. However, although various DL-based methods have been introduced, most of them only focus…
Domain adaptive object detection aims to adapt detection models to domains where annotated data is unavailable. Existing methods have been proposed to address the domain gap using the semi-supervised student-teacher framework. However, a…
This paper presents a new formulation for model-free robust optimal regulation of continuous-time nonlinear systems. The proposed reinforcement learning based approach, referred to as incremental adaptive dynamic programming (IADP),…