English

Effectiveness Assessment of Recent Large Vision-Language Models

Computer Vision and Pattern Recognition 2024-10-29 v5 Artificial Intelligence Machine Learning

Abstract

The advent of large vision-language models (LVLMs) represents a remarkable advance in the quest for artificial general intelligence. However, the model's effectiveness in both specialized and general tasks warrants further investigation. This paper endeavors to evaluate the competency of popular LVLMs in specialized and general tasks, respectively, aiming to offer a comprehensive understanding of these novel models. To gauge their effectiveness in specialized tasks, we employ six challenging tasks in three different application scenarios: natural, healthcare, and industrial. These six tasks include salient/camouflaged/transparent object detection, as well as polyp detection, skin lesion detection, and industrial anomaly detection. We examine the performance of three recent open-source LVLMs, including MiniGPT-v2, LLaVA-1.5, and Shikra, on both visual recognition and localization in these tasks. Moreover, we conduct empirical investigations utilizing the aforementioned LVLMs together with GPT-4V, assessing their multi-modal understanding capabilities in general tasks including object counting, absurd question answering, affordance reasoning, attribute recognition, and spatial relation reasoning. Our investigations reveal that these LVLMs demonstrate limited proficiency not only in specialized tasks but also in general tasks. We delve deep into this inadequacy and uncover several potential factors, including limited cognition in specialized tasks, object hallucination, text-to-image interference, and decreased robustness in complex problems. We hope that this study can provide useful insights for the future development of LVLMs, helping researchers improve LVLMs for both general and specialized applications.

Keywords

Cite

@article{arxiv.2403.04306,
  title  = {Effectiveness Assessment of Recent Large Vision-Language Models},
  author = {Yao Jiang and Xinyu Yan and Ge-Peng Ji and Keren Fu and Meijun Sun and Huan Xiong and Deng-Ping Fan and Fahad Shahbaz Khan},
  journal= {arXiv preprint arXiv:2403.04306},
  year   = {2024}
}

Comments

Accepted by Visual Intelligence

R2 v1 2026-06-28T15:11:59.882Z