Related papers: Class Imbalance in Anomaly Detection: Learning fro…

Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory. The ratio fluctuation of new samples to old exemplars, which is caused by the variation…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Deep Learning is emerging as an effective technique to detect sophisticated cyber-attacks targeting Industrial Control Systems (ICSs). The conventional approach to detection in literature is to learn the "normal" behaviour of the system, to…

Corner cases are the main bottlenecks when applying Artificial Intelligence (AI) systems to safety-critical applications. An AI system should be intelligent enough to detect such situations so that system developers can prepare for…

The vast majority of real world classification problems are imbalanced, meaning there are far fewer data from the class of interest (the positive class) than from other classes. We propose two machine learning algorithms to handle highly…

Anomaly Detection is a relevant problem in numerous real-world applications, especially when dealing with images. However, little attention has been paid to the issue of changes over time in the input data distribution, which may cause a…

Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from…

Most classification algorithms used in high energy physics fall under the category of supervised machine learning. Such methods require a training set containing both signal and background events and are prone to classification errors…

Anomaly detection is an important problem in many application areas, such as network security. Many deep learning methods for unsupervised anomaly detection produce good empirical performance but lack theoretical guarantees. By casting…

In most machine learning applications, classification accuracy is not the primary metric of interest. Binary classifiers which face class imbalance are often evaluated by the $F_\beta$ score, area under the precision-recall curve, Precision…

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find…

Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for…

The detection of anomalous sounds in machinery operation presents a significant challenge due to the difficulty in generalizing anomalous acoustic patterns. This task is typically approached as an unsupervised learning or novelty detection…

Batch Normalization (BN) and its variants has been extensively studied for neural nets in various computer vision tasks, but relatively little work has been dedicated to studying the effect of BN in continual learning. To that end, we…

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…

Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion, its performance scales poorly with dataset complexity. On…

Video anomaly detection is often seen as one-class classification (OCC) problem due to the limited availability of anomaly examples. Typically, to tackle this problem, an autoencoder (AE) is trained to reconstruct the input with training…

Continual learning enables AI models to learn new data sequentially without retraining in real-world scenarios. Most existing methods assume the training data are balanced, aiming to reduce the catastrophic forgetting problem that models…

In this work, we define cost-free learning (CFL) formally in comparison with cost-sensitive learning (CSL). The main difference between them is that a CFL approach seeks optimal classification results without requiring any cost information,…