M3OOD: Automatic Selection of Multimodal OOD Detectors

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qin, Yuehan, Li, Li, Cao, Defu, Yang, Tiankai, Li, Jiate, Zhao, Yue
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911457667448832
author Qin, Yuehan
Li, Li
Cao, Defu
Yang, Tiankai
Li, Jiate
Zhao, Yue
author_facet Qin, Yuehan
Li, Li
Cao, Defu
Yang, Tiankai
Li, Jiate
Zhao, Yue
contents Out-of-distribution (OOD) robustness is a critical challenge for modern machine learning systems, particularly as they increasingly operate in multimodal settings involving inputs like video, audio, and sensor data. Currently, many OOD detection methods have been proposed, each with different designs targeting various distribution shifts. A single OOD detector may not prevail across all the scenarios; therefore, how can we automatically select an ideal OOD detection model for different distribution shifts? Due to the inherent unsupervised nature of the OOD detection task, it is difficult to predict model performance and find a universally Best model. Also, systematically comparing models on the new unseen data is costly or even impractical. To address this challenge, we introduce M3OOD, a meta-learning-based framework for OOD detector selection in multimodal settings. Meta learning offers a solution by learning from historical model behaviors, enabling rapid adaptation to new data distribution shifts with minimal supervision. Our approach combines multimodal embeddings with handcrafted meta-features that capture distributional and cross-modal characteristics to represent datasets. By leveraging historical performance across diverse multimodal benchmarks, M3OOD can recommend suitable detectors for a new data distribution shift. Experimental evaluation demonstrates that M3OOD consistently outperforms 10 competitive baselines across 12 test scenarios with minimal computational overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11936
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M3OOD: Automatic Selection of Multimodal OOD Detectors
Qin, Yuehan
Li, Li
Cao, Defu
Yang, Tiankai
Li, Jiate
Zhao, Yue
Machine Learning
Out-of-distribution (OOD) robustness is a critical challenge for modern machine learning systems, particularly as they increasingly operate in multimodal settings involving inputs like video, audio, and sensor data. Currently, many OOD detection methods have been proposed, each with different designs targeting various distribution shifts. A single OOD detector may not prevail across all the scenarios; therefore, how can we automatically select an ideal OOD detection model for different distribution shifts? Due to the inherent unsupervised nature of the OOD detection task, it is difficult to predict model performance and find a universally Best model. Also, systematically comparing models on the new unseen data is costly or even impractical. To address this challenge, we introduce M3OOD, a meta-learning-based framework for OOD detector selection in multimodal settings. Meta learning offers a solution by learning from historical model behaviors, enabling rapid adaptation to new data distribution shifts with minimal supervision. Our approach combines multimodal embeddings with handcrafted meta-features that capture distributional and cross-modal characteristics to represent datasets. By leveraging historical performance across diverse multimodal benchmarks, M3OOD can recommend suitable detectors for a new data distribution shift. Experimental evaluation demonstrates that M3OOD consistently outperforms 10 competitive baselines across 12 test scenarios with minimal computational overhead.
title M3OOD: Automatic Selection of Multimodal OOD Detectors
topic Machine Learning
url https://arxiv.org/abs/2508.11936