Saved in:
Bibliographic Details
Main Authors: Zhang, Wenyu, Ng, Wei En, Ma, Lixin, Wang, Yuwen, Zhao, Junqi, Koenecke, Allison, Li, Boyang, Wang, Lu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.12693
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910993785815040
author Zhang, Wenyu
Ng, Wei En
Ma, Lixin
Wang, Yuwen
Zhao, Junqi
Koenecke, Allison
Li, Boyang
Wang, Lu
author_facet Zhang, Wenyu
Ng, Wei En
Ma, Lixin
Wang, Yuwen
Zhao, Junqi
Koenecke, Allison
Li, Boyang
Wang, Lu
contents Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework supported by a new human-annotated dataset. SPHERE systematically probes models across increasing levels of complexity, from fundamental skills to multi-skill integration and high-level reasoning that combines spatial, visual, and logical understanding. Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity, understanding both egocentric and allocentric perspectives, and applying spatial logic in physical contexts. These findings expose critical blind spots in existing models and underscore the need for more advanced spatial reasoning techniques, driving the development of vision-language models that align more closely with human spatial cognition. The SPHERE benchmark is available at https://github.com/zwenyu/SPHERE-VLM.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12693
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation
Zhang, Wenyu
Ng, Wei En
Ma, Lixin
Wang, Yuwen
Zhao, Junqi
Koenecke, Allison
Li, Boyang
Wang, Lu
Computer Vision and Pattern Recognition
Artificial Intelligence
Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework supported by a new human-annotated dataset. SPHERE systematically probes models across increasing levels of complexity, from fundamental skills to multi-skill integration and high-level reasoning that combines spatial, visual, and logical understanding. Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity, understanding both egocentric and allocentric perspectives, and applying spatial logic in physical contexts. These findings expose critical blind spots in existing models and underscore the need for more advanced spatial reasoning techniques, driving the development of vision-language models that align more closely with human spatial cognition. The SPHERE benchmark is available at https://github.com/zwenyu/SPHERE-VLM.
title SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.12693