Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Born, Frieda, Neuhäuser, Tom, Muttenthaler, Lukas, Roads, Brett D., Spitzer, Bernhard, Lampinen, Andrew K., Jones, Matt, Müller, Klaus-Robert, Mozer, Michael C.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.13883
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913035252137984
author Born, Frieda
Neuhäuser, Tom
Muttenthaler, Lukas
Roads, Brett D.
Spitzer, Bernhard
Lampinen, Andrew K.
Jones, Matt
Müller, Klaus-Robert
Mozer, Michael C.
author_facet Born, Frieda
Neuhäuser, Tom
Muttenthaler, Lukas
Roads, Brett D.
Spitzer, Bernhard
Lampinen, Andrew K.
Jones, Matt
Müller, Klaus-Robert
Mozer, Michael C.
contents Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans process information. Because humans are constantly adapting to their environment, they represent objects and their relationships in a highly context-sensitive manner. To address this gap, we propose a method for context-sensitive similarity computation from neural network embeddings, applied to modeling a triplet odd-one-out task with an anchor image serving as simultaneous context. Modeling context enables us to achieve up to a 15% improvement in odd-one-out accuracy over a context-insensitive model. We find that this improvement is consistent across both original and "human-aligned" vision foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13883
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Context Sensitivity Improves Human-Machine Visual Alignment
Born, Frieda
Neuhäuser, Tom
Muttenthaler, Lukas
Roads, Brett D.
Spitzer, Bernhard
Lampinen, Andrew K.
Jones, Matt
Müller, Klaus-Robert
Mozer, Michael C.
Computer Vision and Pattern Recognition
Machine Learning
Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans process information. Because humans are constantly adapting to their environment, they represent objects and their relationships in a highly context-sensitive manner. To address this gap, we propose a method for context-sensitive similarity computation from neural network embeddings, applied to modeling a triplet odd-one-out task with an anchor image serving as simultaneous context. Modeling context enables us to achieve up to a 15% improvement in odd-one-out accuracy over a context-insensitive model. We find that this improvement is consistent across both original and "human-aligned" vision foundation models.
title Context Sensitivity Improves Human-Machine Visual Alignment
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.13883