Taxonomy-Aware Evaluation of Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Snæbjarnarson, Vésteinn, Du, Kevin, Stoehr, Niklas, Belongie, Serge, Cotterell, Ryan, Lang, Nico, Frank, Stella
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916676823416832
author Snæbjarnarson, Vésteinn
Du, Kevin
Stoehr, Niklas
Belongie, Serge
Cotterell, Ryan
Lang, Nico
Frank, Stella
author_facet Snæbjarnarson, Vésteinn
Du, Kevin
Stoehr, Niklas
Belongie, Serge
Cotterell, Ryan
Lang, Nico
Frank, Stella
contents When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This raises two issues for evaluation: First, the unconstrained generated text needs to be mapped to the evaluation label space (i.e., 'conifer'). Second, a useful classification measure should give partial credit to less-specific, but not incorrect, answers ('norway spruce' being a type of 'conifer'). To meet these requirements, we propose a framework for evaluating unconstrained text predictions, such as those generated from a vision-language model, against a taxonomy. Specifically, we propose the use of hierarchical precision and recall measures to assess the level of correctness and specificity of predictions with regard to a taxonomy. Experimentally, we first show that existing text similarity measures do not capture taxonomic similarity well. We then develop and compare different methods to map textual VLM predictions onto a taxonomy. This allows us to compute hierarchical similarity measures between the generated text and the ground truth labels. Finally, we analyze modern VLMs on fine-grained visual classification tasks based on our proposed taxonomic evaluation scheme.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Taxonomy-Aware Evaluation of Vision-Language Models
Snæbjarnarson, Vésteinn
Du, Kevin
Stoehr, Niklas
Belongie, Serge
Cotterell, Ryan
Lang, Nico
Frank, Stella
Computer Vision and Pattern Recognition
When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This raises two issues for evaluation: First, the unconstrained generated text needs to be mapped to the evaluation label space (i.e., 'conifer'). Second, a useful classification measure should give partial credit to less-specific, but not incorrect, answers ('norway spruce' being a type of 'conifer'). To meet these requirements, we propose a framework for evaluating unconstrained text predictions, such as those generated from a vision-language model, against a taxonomy. Specifically, we propose the use of hierarchical precision and recall measures to assess the level of correctness and specificity of predictions with regard to a taxonomy. Experimentally, we first show that existing text similarity measures do not capture taxonomic similarity well. We then develop and compare different methods to map textual VLM predictions onto a taxonomy. This allows us to compute hierarchical similarity measures between the generated text and the ground truth labels. Finally, we analyze modern VLMs on fine-grained visual classification tasks based on our proposed taxonomic evaluation scheme.
title Taxonomy-Aware Evaluation of Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.05457