aiqbench analysis
This research introduces a novel unsupervised anomaly detection method that directly aligns latent features with the exact One-Class SVM optimization problem, avoiding common approximations found in current state-of-the-art models. By coupling representation learning tightly with OCSVM decision boundaries, the approach demonstrates superior robustness to domain shifts and successfully identifies subtle anomalies in medical imaging tasks like brain MRI lesion detection. The work advances machine learning by offering a more expressive and reliable framework for scenarios where labeled anomaly data is scarce or unavailable.
OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection
arXiv:2507.21164v3 Announce Type: replace-cross Abstract: Unsupervised anomaly detection (UAD) aims to detect anomalies without labeled data, a necessity in many machine learning applications where anomalous samples are rare or not available. Most state-of-the-art methods fall into two categories: reconstruction-based approaches, which often reconstruct anomalies too well, and decoupled representation learning with density estimators, which can suffer from suboptimal feature spaces. While some recent methods attempt to couple feature learning and anomaly detection, they often rely on surrogate objectives, restrict kernel choices, or introduce approximations that limit their expressiveness and robustness. To address this challenge, we propose a novel method that couples representation learning the exact One-Class SVM (OCSVM) optimization problem, through a custom loss formulation that directly aligns latent features with the OCSVM decision boundary. The model is evaluated on two tasks: a benchmark based on MNIST-C, and a challenging brain MRI lesion detection task. Unlike most methods that focus on large, hyperintense lesions at the image level, our approach succeeds to target small, non-hyperintense lesions, while we evaluate voxel-wise metrics, addressing a more clinically relevant scenario. Both experiments evaluate a form of robustness to domain shifts, including corruption types in MNIST-C and texture or population age variations in MRI. Results demonstrate performance and robustness of our proposed model, highlighting its potential for general UAD and real-world medical imaging applications. The source code is available at https://github.com/Nicolas-Pinon/uad\_ocsvm\_guided\_repr\_learning.
Abstract:Unsupervised anomaly detection (UAD) aims to detect anomalies without labeled data, a necessity in many machine learning applications where anomalous samples are rare or not available. Most state-of-the-art methods fall into two categories: reconstruction-based approaches, which often reconstruct anomalies too well, and decoupled representation learning with density estimators, which can suffer from suboptimal feature spaces. While some recent methods attempt to couple feature learning and anomaly detection, they often rely on surrogate objectives, restrict kernel choices, or introduce approximations that limit their expressiveness and robustness. To address this challenge, we propose a novel method that couples representation learning the exact One-Class SVM (OCSVM) optimization problem, through a custom loss formulation that directly aligns latent features with the OCSVM decision boundary. The model is evaluated on two tasks: a benchmark based on MNIST-C, and a challenging brain MRI lesion detection task. Unlike most methods that focus on large, hyperintense lesions at the image level, our approach succeeds to target small, non-hyperintense lesions, while we evaluate voxel-wise metrics, addressing a more clinically relevant scenario. Both experiments evaluate a form of robustness to domain shifts, including corruption types in MNIST-C and texture or population age variations in MRI. Results demonstrate performance and robustness of our proposed model, highlighting its potential for general UAD and real-world medical imaging applications. The source code is available at this https URL\_ocsvm\_guided\_repr\_learning.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV); Machine Learning (stat.ML)
arXiv:2507.21164 [cs.LG]
(or arXiv:2507.21164v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2507.21164 Focus to learn more arXiv-issued DOI via DataCite
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.
Full text under the publisher's open licence · 327 words
Related coverage
OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection
arXiv · Jun 12, 2026
Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection
arXiv · Aug 6, 2026
Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detection
arXiv · Sep 29, 2026
TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection
arXiv · Jun 5, 2026