Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models


Bin Fu (Institute of Computing Technology, Chinese Academy of Sciences), Qiyang Wan (Institute of Computing Technology, Chinese Academy of Sciences), Jialin Li (Institute of Computing Technology, Chinese Academy of Sciences), Ruiping Wang (Institute of Computing Technology, Chinese Academy of Sciences), Xilin Chen (Institute of Computing Technology)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Categorization, a core cognitive ability in humans that organizes objects based on common features, is essential to cognitive science as well as computer vision. To evaluate the categorization ability of visual AI models, various proxy tasks on recognition from datasets to open world scenarios have been proposed. Recent development of Large Multimodal Models (LMMs) has demonstrated impressive results in high-level visual tasks, such as visual question answering, video temporal reasoning, etc., utilizing the advanced architectures and large-scale multimodal instruction tuning. Previous researchers have developed holistic benchmarks to measure the high-level visual capability of LMMs, but there is still a lack of pure and in-depth quantitative evaluation of the most fundamental categorization ability. According to the research on human cognitive process, categorization can be seen as including two parts: category learning and category use. Inspired by this, we propose a novel, challenging, and efficient benchmark based on composite blocks, called **ComBo**, which provides a disentangled evaluation framework and covers the entire categorization process from learning to use. By analyzing the results of multiple evaluation tasks, we find that although LMMs exhibit acceptable generalization ability in learning new categories, there are still gaps compared to humans in many ways, such as fine-grained perception of spatial relationship and abstract category understanding. Through the study of categorization, we can provide inspiration for the further development of LMMs in terms of interpretability and generalization.

Citation

@inproceedings{Fu_2024_BMVC,
author    = {Bin Fu and Qiyang Wan and Jialin Li and Ruiping Wang and Xilin Chen},
title     = {Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0887.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection