Democratizing Fine-grained Visual Recognition with Large Language Models

arXiv:2401.13837v2 Announce Type: replace
Abstract: Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average layperson does not excel at differentiating species of birds or mushrooms due to subtle differences among the species. A major bottleneck in developing FGVR systems is caused by the need of high-quality paired expert annotations. To circumvent the need of expert knowledge we propose …

abstract applications arxiv birds computer computer vision cs.cv differences excel fine-grained images language language models large language large language models recognition significance species type vision visual world