Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Elmansoury, Sary, Mesabah, Islam, Großmann, Gerrit, Neigel, Peter, Bhalwankar, Raj, Kondermann, Daniel, Vollmer, Sebastian J.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.09732
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909783203774464
author Elmansoury, Sary
Mesabah, Islam
Großmann, Gerrit
Neigel, Peter
Bhalwankar, Raj
Kondermann, Daniel
Vollmer, Sebastian J.
author_facet Elmansoury, Sary
Mesabah, Islam
Großmann, Gerrit
Neigel, Peter
Bhalwankar, Raj
Kondermann, Daniel
Vollmer, Sebastian J.
contents Vision language models (VLMs) excel at zero-shot visual classification, but their performance on fine-grained tasks and large hierarchical label spaces is understudied. This paper investigates whether structured, tree-based reasoning can enhance VLM performance. We introduce a framework that decomposes classification into interpretable decisions using decision trees and evaluates it on fine-grained (GTSRB) and coarse-grained (CIFAR-10) datasets. Although the model achieves 98.2% accuracy in understanding the tree knowledge, tree-based reasoning consistently underperforms standard zero-shot prompting. We also explore enhancing the tree prompts with LLM-generated classes and image descriptions to improve alignment. The added description enhances the performance of the tree-based and zero-shot methods. Our findings highlight limitations of structured reasoning in visual classification and offer insights for designing more interpretable VLM systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09732
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs
Elmansoury, Sary
Mesabah, Islam
Großmann, Gerrit
Neigel, Peter
Bhalwankar, Raj
Kondermann, Daniel
Vollmer, Sebastian J.
Computer Vision and Pattern Recognition
Vision language models (VLMs) excel at zero-shot visual classification, but their performance on fine-grained tasks and large hierarchical label spaces is understudied. This paper investigates whether structured, tree-based reasoning can enhance VLM performance. We introduce a framework that decomposes classification into interpretable decisions using decision trees and evaluates it on fine-grained (GTSRB) and coarse-grained (CIFAR-10) datasets. Although the model achieves 98.2% accuracy in understanding the tree knowledge, tree-based reasoning consistently underperforms standard zero-shot prompting. We also explore enhancing the tree prompts with LLM-generated classes and image descriptions to improve alignment. The added description enhances the performance of the tree-based and zero-shot methods. Our findings highlight limitations of structured reasoning in visual classification and offer insights for designing more interpretable VLM systems.
title Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.09732