<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-rethinking">
    <titleInfo>
        <title>Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhenhailong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hang</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manling</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Han</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heng</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models</title>
        </titleInfo>
        <originInfo>
            <publisher>International Conference on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Virtual</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Despite achieving state-of-the-art zero-shot performance, existing vision-language models still fall short of few-shot transfer ability on domain-specific problems. Classical fine-tuning often fails to prevent highly expressive models from exploiting spurious correlations. Although model-agnostic meta-learning (MAML) presents as a natural alternative for few-shot transfer learning, the expensive computation due to implicit second-order optimization limits its use on large-scale vision-language models such as CLIP. While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML. To show the impact of task sampling, we propose a simple algorithm, Model-Agnostic Multitask Fine-tuning (MAMF), which differentiates classical fine-tuning only on uniformly sampling multiple tasks. Despite its simplicity, we show that MAMF consistently outperforms classical fine-tuning on five few-shot image classification tasks. We further show that the effectiveness of the bi-level optimization in MAML is highly sensitive to the zero-shot performance of a task in the context of few-shot vision-language classification. The goal of this paper is to provide new insights on what makes few-shot learning work, and encourage more research into investigating better task sampling strategies.</abstract>
    <identifier type="citekey">wang-etal-2022-rethinking</identifier>
    <location>
        <url>https://aclanthology.org/2022.mmmpie-1.2</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>7</start>
            <end>14</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning
%A Wang, Zhenhailong
%A Yu, Hang
%A Li, Manling
%A Zhao, Han
%A Ji, Heng
%S Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Virtual
%F wang-etal-2022-rethinking
%X Despite achieving state-of-the-art zero-shot performance, existing vision-language models still fall short of few-shot transfer ability on domain-specific problems. Classical fine-tuning often fails to prevent highly expressive models from exploiting spurious correlations. Although model-agnostic meta-learning (MAML) presents as a natural alternative for few-shot transfer learning, the expensive computation due to implicit second-order optimization limits its use on large-scale vision-language models such as CLIP. While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML. To show the impact of task sampling, we propose a simple algorithm, Model-Agnostic Multitask Fine-tuning (MAMF), which differentiates classical fine-tuning only on uniformly sampling multiple tasks. Despite its simplicity, we show that MAMF consistently outperforms classical fine-tuning on five few-shot image classification tasks. We further show that the effectiveness of the bi-level optimization in MAML is highly sensitive to the zero-shot performance of a task in the context of few-shot vision-language classification. The goal of this paper is to provide new insights on what makes few-shot learning work, and encourage more research into investigating better task sampling strategies.
%U https://aclanthology.org/2022.mmmpie-1.2
%P 7-14

Markdown (Informal)

[Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning](https://aclanthology.org/2022.mmmpie-1.2) (Wang et al., MMMPIE 2022)

• Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning (Wang et al., MMMPIE 2022)

ACL

• Zhenhailong Wang, Hang Yu, Manling Li, Han Zhao, and Heng Ji. 2022. Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning. In Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models, pages 7–14, Virtual. International Conference on Computational Linguistics.