Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.14149 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914042927382528 |
|---|---|
| author | Li, Haotian Jiao, Jianbo |
| author_facet | Li, Haotian Jiao, Jianbo |
| contents | Imagine living in a world composed solely of primitive shapes, could you still recognise familiar objects? Recent studies have shown that abstract images-constructed by primitive shapes-can indeed convey visual semantic information to deep learning models. However, representations obtained from such images often fall short compared to those derived from traditional raster images. In this paper, we study the reasons behind this performance gap and investigate how much high-level semantic content can be captured at different abstraction levels. To this end, we introduce the Hierarchical Abstraction Image Dataset (HAID), a novel data collection that comprises abstract images generated from normal raster images at multiple levels of abstraction. We then train and evaluate conventional vision systems on HAID across various tasks including classification, segmentation, and object detection, providing a comprehensive study between rasterised and abstract image representations. We also discuss if the abstract image can be considered as a potentially effective format for conveying visual semantic information and contributing to vision tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Exploratory Study on Abstract Images and Visual Representations Learned from Them Li, Haotian Jiao, Jianbo Computer Vision and Pattern Recognition Imagine living in a world composed solely of primitive shapes, could you still recognise familiar objects? Recent studies have shown that abstract images-constructed by primitive shapes-can indeed convey visual semantic information to deep learning models. However, representations obtained from such images often fall short compared to those derived from traditional raster images. In this paper, we study the reasons behind this performance gap and investigate how much high-level semantic content can be captured at different abstraction levels. To this end, we introduce the Hierarchical Abstraction Image Dataset (HAID), a novel data collection that comprises abstract images generated from normal raster images at multiple levels of abstraction. We then train and evaluate conventional vision systems on HAID across various tasks including classification, segmentation, and object detection, providing a comprehensive study between rasterised and abstract image representations. We also discuss if the abstract image can be considered as a potentially effective format for conveying visual semantic information and contributing to vision tasks. |
| title | An Exploratory Study on Abstract Images and Visual Representations Learned from Them |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.14149 |