analiza aiqbench
This research introduces ContCore, an algorithm for continual anomaly detection that maintains fixed memory constraints while preventing catastrophic forgetting in sequential tasks. By iteratively refining a compact data summary rather than relying on unbounded storage or neural networks prone to degradation, the method offers theoretical guarantees and state-of-the-art performance across multiple benchmarks. The approach is significant for deploying robust AI monitoring systems where long-term operational efficiency and limited computational resources are critical factors.
Memory-Bounded Continuation of Greedy Sampling for Continual Anomaly Detection
arXiv:2608.15277v1 Announce Type: cross Abstract: Greedy sampling produces a compact yet representative summary of normal data, which is essential for reliable anomaly detection that relies on measuring distance from normality. For continual anomaly detection where tasks arrive sequentially, extending greedy sampling is straightforward with unbounded memory through coreset accumulation. However, practical deployment requires fixed memory where the coreset size remains constant regardless of task count. We observe that continued greedy sampling, which iteratively applies greedy selection over previously greedy-sampled sets, effectively preserves representativeness under strict memory limits. Despite discarding data at each step to satisfy the memory constraint, coreset quality degrades gracefully rather than catastrophically, enabling reliable anomaly detection across the tasks. We provide theoretical justification by showing that resulting greedy-continued coreset approximates the oracle coreset within a bounded gap. We instantiate this principle in ContCore, which constructs a greedy-continued coreset through greedy expansion on new task features followed by greedy consolidation to enforce the memory budget. Unlike neural methods susceptible to catastrophic forgetting or naive coreset accumulation requiring unbounded memory, ContCore maintains fixed memory with theoretical guarantees. Empirically, ContCore achieves state-of-the-art performance across 11 task schedules on MVTecAD and VisA, and extends effectively to online continual AD settings where prior methods degrade significantly. Code: https://github.com/jungyg/ContCore
Abstract:Greedy sampling produces a compact yet representative summary of normal data, which is essential for reliable anomaly detection that relies on measuring distance from normality. For continual anomaly detection where tasks arrive sequentially, extending greedy sampling is straightforward with unbounded memory through coreset accumulation. However, practical deployment requires fixed memory where the coreset size remains constant regardless of task count. We observe that continued greedy sampling, which iteratively applies greedy selection over previously greedy-sampled sets, effectively preserves representativeness under strict memory limits. Despite discarding data at each step to satisfy the memory constraint, coreset quality degrades gracefully rather than catastrophically, enabling reliable anomaly detection across the tasks. We provide theoretical justification by showing that resulting greedy-continued coreset approximates the oracle coreset within a bounded gap. We instantiate this principle in ContCore, which constructs a greedy-continued coreset through greedy expansion on new task features followed by greedy consolidation to enforce the memory budget. Unlike neural methods susceptible to catastrophic forgetting or naive coreset accumulation requiring unbounded memory, ContCore maintains fixed memory with theoretical guarantees. Empirically, ContCore achieves state-of-the-art performance across 11 task schedules on MVTecAD and VisA, and extends effectively to online continual AD settings where prior methods degrade significantly. Code: this https URL
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2608.15277 [cs.CV]
(or arXiv:2608.15277v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.15277 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 303 cuvinte
Subiecte conexe
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · 4 sept. 2026
How might continual learning affect safety and alignment?
LessWrong · 13 iun. 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026
Presentation: Exploding GPUs
InfoQ · 16 oct. 2026