Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers ...

• Motivate benefits of rehearsal-based continual learning for scientific applications.
• Define rehearsal buffers and introduce extensions for data-parallel training.
• Present key design principles, including asynchronous buffer ...

Continual learning refers to the capability of a machine learning model to learn and adapt to new information, without compromising its performance on previously learned tasks. Although several studies have investigated continual learning methods ...

• A continual learning framework is proposed and implemented for continuous neural information retrieval tasks.
• A dataset called Topic-MSMARCO, containing diverse topics for continual neural information retrieval tasks, is provided.
• ...

Zero-shot learning aims to recognize objects from novel concepts through the model trained on seen class data and assisted by the semantic descriptions. Though it breaks the serious reliance on training data, it still fails to deal with the ...

• We summarize the IZSL challenges as task-recency bias and seen-class bias.
• We propose to learn consistent representation joint an adaptive adjustment strategy.
• The method needs limited memory footprint to store the fixed scale ...

The rapid development of large-scale language models has garnered widespread interest from both academia and industry. Efficiently applying those models across various domains is now posing a challenge to researchers. High training costs and the ...

Continual learning (CL) has emerged as an important avenue of research in recent years, at the intersection of Machine Learning (ML) and Human–Robot Interaction (HRI), to allow robots to continually learn in their environments over long-term interactions ...

Continual visual search has attracted increasing attention due to its practicality. It aims to continuously extract embeddings for new-emerging gallery data while keeping previously generated embeddings unchanged. The primary challenge lies in ...

Industry 5.0 (I5.0) is increasingly governed by Operation Technology and Information Technology. It hosts Deep Learning (DL) solutions as a premier tool for the informatization of Quality Inspection (QI) of Mass Produced Products (MPP) and Mass ...

• A customer order-driven informatization framework for mass-customized products.
• A hybrid PackMASNet scheme that minimizes mass-produced and customized products’ performance degradation.
• Lightweight Cosine-similarity threshold-based ...

The rapid advancement of wearable technology has enabled continuous, real-time health monitoring through devices such as smartwatches and fitness trackers. These devices generate vast amounts of biometric data, including heart rate, galvanic skin ...

In recent years, there has been remarkable progress in the field of digital pathology, driven by the ability to model complex tissue patterns using advanced deep-learning algorithms. However, the robustness of these models is often severely ...

Deep Neural Networks achieve outstanding results; however, their reliance on a static environment with fixed data poses challenges in dynamic scenarios where data continuously evolves. Being capable of learning, adapting, and generalizing ...

Learning algorithms in modern information systems often operate in dynamic environments where data is collected as transient data streams. Processing data streams imposes new computational requirements on algorithms compared to static data mining,...

• A novel hybrid architecture for evolving streaming classification is proposed, which combines the advantages of ensemble learning and neural network.
• A chunk-mode drift detector for monitoring drift occurring in infinite streaming data ...

Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database. However, in clinical ...

Deep learning has been extensively used in various medical scenarios. However, the data-hungry nature of deep learning poses significant challenges in the medical domain, where data is often private, scarce, and imbalanced. Federated learning ...

Large language models (LLMs) have demonstrated potential across various tasks, including vision-language applications like chest X-ray (XR) report generation (RG) in healthcare. Recent RG approaches focus on optimizing model performance for a ...

Despite extensive algorithms for epilepsy prediction via machine learning, most models are tailored for offline scenarios and cannot handle actual scenarios where data changes over time. Catastrophic forgetting(CF) for learned ...

• Proposed Patient-IL adapts to dynamic patient increase for seizure prediction, facilitating EEG-based incremental learning studies.
• Proposed MP strategy tackles CF in epilepsy prediction due to EEG data interference, integrating ...

Multi-modal models such as CLIP possess remarkable zero-shot transfer capabilities, making them highly effective in continual learning tasks. However, this advantage is severely compromised by catastrophic forgetting, which undermines the valuable ...

Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks. Despite notable progress in continual classification, systems designed for complex vision tasks such as detection or ...

Prompt-based Continual Learning (PCL) has gained considerable attention as a promising continual learning solution because it achieves state-of-the-art performance while preventing privacy violations and memory overhead problems. Nonetheless, ...$$$$$$$$

Remote photoplethysmography (rPPG) has gained significant attention in recent years for its ability to extract physiological signals from facial videos. While existing rPPG measurement methods have shown satisfactory performance in intra-dataset ...

We propose an approach for anytime continual learning (AnytimeCL) for open vocabulary image classification. The AnytimeCL problem aims to break away from batch training and rigid models by requiring that a system can predict any set of labels at ...