NeurIPS 2025 | ADPretrain：工业异常检测预训练框架，性能飞跃新突破

上海交通大学和南京农业大学的研究团队在 NeurIPS 2025 上发表了名为 ADPretrain的新框架，该框架专为工业异常检测（Industrial Anomaly Detection, IAD）任务设计，旨在解决现有方法过度依赖 ImageNet 预训练特征所带来的局限性。这一研究成果为工业界带来了全新的视角，预示着 预训练在特定领域应用的巨大潜力。 工业异常检测的“水土不服” 目前，工业 ...

NeurIPS 2025 重磅：上交大ADPretrain，工业异常检测预训练迎“范式革新”

近日，备受瞩目的机器学习顶级会议 NeurIPS 2025公布了最新论文录用结果，其中来自上海交通大学和南京农业大学的研究团队提出的 ADPretrain框架，凭借其在工业异常检测领域的卓越表现，引发了广泛关注。这项研究针对现有异常检测方法过度依赖 ImageNet预训练特征，导致在工业场景中“水土不服”的问题，提出了创新的解决方案，为工业 AI应用带来了新的突破。 ADPretrain 框架的核 ...

Arctera Expands AI-powered Real-time Anomaly Detection for All Data, Any App, Anywhere

Arctera, a global leader in data management, today announced new AI-powered features in Arctera InfoScale that enable organizations to identify and respond to ransomware indicators in real time. By ...
Deccan Chronicle

AI Transforms Supply Chain Monitoring with Real-Time Anomaly Detection

Enterprises deploy machine learning within SAP and cloud pipelines to catch data errors instantly and boost efficiency ...
Statetechmagazine

State and Local Agencies Can Identify Cyberthreats Through Anomaly Detection

Doug Bonderud is an award-winning writer capable of bridging the gap between complex and conversational across technology, innovation and the human condition. By defining a set of normal user and ...
TechCrunch

Financial firms should leverage machine learning to make anomaly detection easier

Anomaly detection is one of the more difficult and underserved operational areas in the asset-servicing sector of financial institutions. Broadly speaking, a true anomaly is one that deviates from the ...

Meta’s SPICE framework pushes AI toward self-learning without human supervision

The new reinforcement learning system lets large language models challenge and improve themselves using real-world data ...