Multi-layer Aggregation as a key to feature-based OOD detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Multi-layer Aggregation as a key to feature-based OOD detection


Deep Learning models are easily disturbed by variations in the input images that were not observed during the training stage, resulting in unpredictable predictions. Detecting such Out-of-Distribution (OOD) images is particularly crucial in the context of medical image analysis, where the range of possible abnormalities is extremely wide. Recently, a new category of methods has emerged, based on the analysis of the intermediate features of a trained model. These methods can be divided into 2 groups: single-layer methods that consider the feature map obtained at a fixed, carefully chosen layer, and multi-layer methods that consider the ensemble of the feature maps generated by the model. While promising, a proper comparison of these algorithms is still lacking. In this work, we compared various feature-based OOD detection methods on a large spectra of OOD (20 types), representing approximately 7800 3D MRIs. Our experiments shed the light on two phenomenons. First, multi-layer methods consistently outperform single-layer approaches, which tend to have inconsistent behaviour depending on the type of anomaly. Second, the OOD detection performance highly depends on the architecture of the underlying neural network.
Fichier principal
Vignette du fichier
multi-layer.pdf (6.28 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04436227 , version 1 (05-02-2024)




Benjamin Lambert, Florence Forbes, Senan Doyle, Michel Dojat. Multi-layer Aggregation as a key to feature-based OOD detection. UNSURE 2023 - 5th International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, Oct 2023, Vancouver, Canada. ⟨10.48550/arXiv.2307.15647⟩. ⟨hal-04436227⟩
41 View
13 Download



Gmail Mastodon Facebook X LinkedIn More