Saved in:
Bibliographic Details
Main Authors: Miller, Dimity, Sünderhauf, Niko, Kenna, Alex, Mason, Keita
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.16528
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914877543546880
author Miller, Dimity
Sünderhauf, Niko
Kenna, Alex
Mason, Keita
author_facet Miller, Dimity
Sünderhauf, Niko
Kenna, Alex
Mason, Keita
contents Are vision-language models (VLMs) for open-vocabulary perception inherently open-set models because they are trained on internet-scale datasets? We answer this question with a clear no - VLMs introduce closed-set assumptions via their finite query set, making them vulnerable to open-set conditions. We systematically evaluate VLMs for open-set recognition and find they frequently misclassify objects not contained in their query set, leading to alarmingly low precision when tuned for high recall and vice versa. We show that naively increasing the size of the query set to contain more and more classes does not mitigate this problem, but instead causes diminishing task performance and open-set performance. We establish a revised definition of the open-set problem for the age of VLMs, define a new benchmark and evaluation protocol to facilitate standardised evaluation and research in this important area, and evaluate promising baseline approaches based on predictive uncertainty and dedicated negative embeddings on a range of open-vocabulary VLM classifiers and object detectors.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16528
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open-Set Recognition in the Age of Vision-Language Models
Miller, Dimity
Sünderhauf, Niko
Kenna, Alex
Mason, Keita
Computer Vision and Pattern Recognition
Are vision-language models (VLMs) for open-vocabulary perception inherently open-set models because they are trained on internet-scale datasets? We answer this question with a clear no - VLMs introduce closed-set assumptions via their finite query set, making them vulnerable to open-set conditions. We systematically evaluate VLMs for open-set recognition and find they frequently misclassify objects not contained in their query set, leading to alarmingly low precision when tuned for high recall and vice versa. We show that naively increasing the size of the query set to contain more and more classes does not mitigate this problem, but instead causes diminishing task performance and open-set performance. We establish a revised definition of the open-set problem for the age of VLMs, define a new benchmark and evaluation protocol to facilitate standardised evaluation and research in this important area, and evaluate promising baseline approaches based on predictive uncertainty and dedicated negative embeddings on a range of open-vocabulary VLM classifiers and object detectors.
title Open-Set Recognition in the Age of Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.16528