<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-2024-enhancing">
    <titleInfo>
        <title>Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Canshi</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">wei-2024-enhancing</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-emnlp.102</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.102/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>1857</start>
            <end>1871</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models
%A Wei, Canshi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F wei-2024-enhancing
%X 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.
%R 10.18653/v1/2024.findings-emnlp.102
%U https://aclanthology.org/2024.findings-emnlp.102/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.102
%P 1857-1871

Markdown (Informal)

[Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models](https://aclanthology.org/2024.findings-emnlp.102/) (Wei, Findings 2024)

• Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models (Wei, Findings 2024)

ACL

• Canshi Wei. 2024. Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1857–1871, Miami, Florida, USA. Association for Computational Linguistics.