@inproceedings{wei-2024-enhancing,
    title = "Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models",
    author = "Wei, Canshi",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-emnlp.102/",
    doi = "10.18653/v1/2024.findings-emnlp.102",
    pages = "1857--1871",
    abstract = "Fine-grained image classification, especially in zero-/few-shot scenarios, poses a considerable challenge for vision-language models (VLMs) like CLIP, which often struggle to differentiate between semantically similar classes due to insufficient supervision for fine-grained tasks. On the other hand, Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in tasks like Visual Question Answering (VQA) but remain underexplored in the context of fine-grained image classification. This paper presents CascadeVLM, a novel framework that harnesses the complementary strengths of both CLIP-like and LVLMs VLMs to tackle these challenges. Using granular knowledge effectively in LVLMs and integrating a cascading approach, CascadeVLM dynamically allocates samples using an entropy threshold, balancing computational efficiency with classification accuracy. Experiments on multiple fine-grained datasets, particularly the Stanford Cars dataset, show that CascadeVLM outperforms existing models, achieving 92{\%} accuracy. Our results highlight the potential of combining VLM and LVLM for robust, efficient and interpretable fine-grained image classification, offering new insights into their synergy."
}