A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models
A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models
Large Vision-Language Models (LVLMs), despite their recent success, are hardly comprehensively tested for their cognitive abilities. Inspired by the prevalent use of the Cookie Theft task in human cognitive tests, we propose a novel evaluation benchmark to evaluate high-level cognitive abilities of LVLMs using images with rich semantics. The benchmark consists of 251 images along with comprehensive annotations. It defines eight reasoning capabilities and comprises an image description task and a visual question answering task. Our evaluation of well-known LVLMs shows that there is still a significant gap in cognitive abilities between LVLMs and humans.
Mengyue Wu、Kenny Q. Zhu、Xiujie Song、Yanyi Chen、Chunhao Zhang
信息科学、信息技术计算技术、计算机技术自然科学研究方法
Mengyue Wu,Kenny Q. Zhu,Xiujie Song,Yanyi Chen,Chunhao Zhang.A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models[EB/OL].(2024-02-28)[2025-07-16].https://arxiv.org/abs/2402.18409.点此复制
评论