36 citations · 81 across the 17 of their papers we have counts for
19 papers
InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection
Łukasz Marcjan, Dorota Wilk-Kołodziejczyk, Roberto Corizzo
Industrial anomaly detection benchmarks have advanced rapidly, yet they remain largely static and therefore underrepresent deployment settings in which inspection systems must be e…
PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
Mateusz Smendowski, Kamil Faber, Piotr Nawrocki +2
Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices…
Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios
Kamil Faber, Mateusz Smendowski, Roberto Corizzo
Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD benchmarks, however, d…
Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts
Taylor Maxson, Roberto Corizzo, Yaning Wu +2
Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific sub…
TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
Dominik Żurek, Kamil Faber, Marcin Pietron +2
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This s…
DNS-GT: A Graph-based Transformer Approach to Learn Embeddings of Domain Names from DNS Queries
Massimiliano Altieri, Ronan Hamon, Roberto Corizzo +2
Network intrusion detection systems play a crucial role in the security strategy employed by organisations to detect and prevent cyberattacks. Such systems usually combine pattern…
xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
Kamil Faber, Marcin Pietroń, Dominik Żurek +1
The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon fo…
TinySubNets: An efficient and low capacity continual learning strategy
Marcin Pietroń, Kamil Faber, Dominik Żurek +1
Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effe…
AD-NEv++ : The multi-architecture neuroevolution-based multivariate anomaly detection framework
Marcin Pietroń, Dominik Żurek, Kamil Faber +1
Anomaly detection tools and methods enable key analytical capabilities in modern cyberphysical and sensor-based systems. Despite the fast-paced development in deep learning archite…
Towards efficient deep autoencoders for multivariate time series anomaly detection
Marcin Pietroń, Dominik Żurek, Kamil Faber +1
Multivariate time series anomaly detection is a crucial problem in many industrial and research applications. Timely detection of anomalies allows, for instance, to prevent defects…
Using LLMs to discover emerging coded antisemitic hate-speech in extremist social media
Dhanush Kikkisetti, Raza Ul Mustafa, Wendy Melillo +4
Online hate speech proliferation has created a difficult problem for social media platforms. A particular challenge relates to the use of coded language by groups interested in bot…
Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting
Marcin Pietroń, Dominik Żurek, Kamil Faber +1
Continual Learning (CL) is a process in which there is still huge gap between human and deep learning model efficiency. Recently, many CL algorithms were designed. Most of them hav…
AD-NEV: A Scalable Multi-level Neuroevolution Framework for Multivariate Anomaly Detection
Marcin Pietron, Dominik Zurek, Kamil Faber +1
Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectur…
From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning
Kamil Faber, Dominik Zurek, Marcin Pietron +3
Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop mode…
Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights
Kamil Faber, Roberto Corizzo, Bartlomiej Sniezynski +1
Anomaly detection is of paramount importance in many real-world domains, characterized by evolving behavior. Lifelong learning represents an emerging trend, answering the need for…
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
Indranil Sur, Zachary Daniels, Abrar Rahman +16
As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adap…
WATCH: Wasserstein Change Point Detection for High-Dimensional Time Series Data
Kamil Faber, Roberto Corizzo, Bartlomiej Sniezynski +2
Detecting relevant changes in dynamic time series data in a timely manner is crucially important for many data analysis tasks in real-world settings. Change point detection methods…
On the combined effect of class imbalance and concept complexity in deep learning
Kushankur Ghosh, Colin Bellinger, Roberto Corizzo +2
Structural concept complexity, class overlap, and data scarcity are some of the most important factors influencing the performance of classifiers under class imbalance conditions.…
ReMix: Calibrated Resampling for Class Imbalance in Deep learning
Colin Bellinger, Roberto Corizzo, Nathalie Japkowicz
Class imbalance is a problem of significant importance in applied deep learning where trained models are exploited for decision support and automated decisions in critical areas su…