paper-with-me

Papers

A Multi-directional Meta-Learning Framework for Class-Generalizable Anomaly Detection

2026-01-27 · Padmaksha Roy, Lamine Mili, Almuatazbellah Boker arxiv

In this paper, we address the problem of class-generalizable anomaly detection, where the objective is to develop a unified model by focusing our learning on the available normal data and a small amount of anomaly data in order to detect the completely unseen anomalies, also referred to as the out-of-distribution (OOD) classes. Adding to this challenge is the fact that the anomaly data is rare and costly to label. To achieve this, we propose a multidirectional meta-learning algorithm -- at the inner level, the model aims to learn the manifold of the normal data (representation); at the outer level, the model is meta-tuned with a few anomaly samples to maximize the softmax confidence margin between the normal and anomaly samples (decision surface calibration), treating normals as in-distribution (ID) and anomalies as out-of-distribution (OOD). By iteratively repeating this process over multiple episodes of predominantly normal and a small number of anomaly samples, we realize a multidirectional meta-learning framework. This two-level optimization, enhanced by multidirectional training, enables stronger generalization to unseen anomaly classes.

📄 PDF Abstract BibTeX arXiv:2601.19833

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection

Similar Papers 제목 키워드 기반

FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation

2024-04-19 · Tianfu Wang, Qilin Fan, Chao Wang, Long Yang 외

Virtual network embedding (VNE) is an essential resource allocation task in network virtualization, aiming to map virtual network requests (VNRs) onto physical infrastructure. Reinforcement learning (RL) has recently eme…

DecoderNetwork EmbeddingReinforcement Learning (RL)Scheduling

Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning

2019-10-05 · ICCV 2019 10 · Limeng Qiao, Yemin Shi, Jia Li, Yao-Wei Wang 외

Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generali…

Few-Shot LearningMeta-LearningMetric Learning

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

2020-12-01 · CVPR 2021 1 · Yuyang Zhao, Zhun Zhong, Fengxiang Yang, Zhiming Luo 외

Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to train a new model for a new domain by acce…

Domain GeneralizationMeta-LearningPerson Re-IdentificationUnsupervised Domain Adaptation

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

2023-08-18 · ICCV 2023 1 · Xiran Wang, Jian Zhang, Lei Qi, Yinghuan Shi

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common …

Domain GeneralizationMeta-Learning

MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models

2024-03-25 · Kailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang 외

Recent advancements in large language models (LLMs) focus on aligning to heterogeneous human expectations and values via multi-objective preference alignment. However, existing methods are dependent on the policy model p…

GPUIn-Context Learning