@inproceedings{gautam-etal-2022-refinement,
title = "Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning",
author = "Gautam, Chandan and
Parameswaran, Sethupathy and
Verma, Vinay and
Sundaram, Suresh and
Ramasamy, Savitha",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.455",
doi = "10.18653/v1/2022.findings-emnlp.455",
pages = "6127--6140",
abstract = "Zero-Shot Learning (ZSL) has shown great promise at the intersection of vision and language, and generative methods for ZSL are predominant owing to their efficiency. Moreover, textual description or attribute plays a critical role in transferring knowledge from the seen to unseen classes in ZSL. Such generative approaches for ZSL are very costly to train and require the class description of the unseen classes during training. In this work, we propose a non-generative gating-based attribute refinement network for ZSL, which achieves similar accuracies to generative methods of ZSL, at a much lower computational cost. The refined attributes are mapped into the visual domain through an attribute embedder, and the whole network is guided by the circle loss and the well-known softmax cross-entropy loss to obtain a robust class embedding. We refer to our approach as Circle loss guided gating-based Attribute-Refinement Network (CARNet). We perform extensive experiments on the five benchmark datasets over the various challenging scenarios viz., Generalized ZSL (GZSL), Continual GZSL (CGZSL), and conventional ZSL. We observe that the CARNet significantly outperforms recent non-generative ZSL methods and most generative ZSL methods in all three settings by a significant margin. Our extensive ablation study disentangles the performance of various components and justifies their importance. The source code is available at \url{https://github.com/Sethup123/CARNet}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gautam-etal-2022-refinement">
<titleInfo>
<title>Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chandan</namePart>
<namePart type="family">Gautam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sethupathy</namePart>
<namePart type="family">Parameswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinay</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suresh</namePart>
<namePart type="family">Sundaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Savitha</namePart>
<namePart type="family">Ramasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-Shot Learning (ZSL) has shown great promise at the intersection of vision and language, and generative methods for ZSL are predominant owing to their efficiency. Moreover, textual description or attribute plays a critical role in transferring knowledge from the seen to unseen classes in ZSL. Such generative approaches for ZSL are very costly to train and require the class description of the unseen classes during training. In this work, we propose a non-generative gating-based attribute refinement network for ZSL, which achieves similar accuracies to generative methods of ZSL, at a much lower computational cost. The refined attributes are mapped into the visual domain through an attribute embedder, and the whole network is guided by the circle loss and the well-known softmax cross-entropy loss to obtain a robust class embedding. We refer to our approach as Circle loss guided gating-based Attribute-Refinement Network (CARNet). We perform extensive experiments on the five benchmark datasets over the various challenging scenarios viz., Generalized ZSL (GZSL), Continual GZSL (CGZSL), and conventional ZSL. We observe that the CARNet significantly outperforms recent non-generative ZSL methods and most generative ZSL methods in all three settings by a significant margin. Our extensive ablation study disentangles the performance of various components and justifies their importance. The source code is available at https://github.com/Sethup123/CARNet.</abstract>
<identifier type="citekey">gautam-etal-2022-refinement</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.455</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.455</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6127</start>
<end>6140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning
%A Gautam, Chandan
%A Parameswaran, Sethupathy
%A Verma, Vinay
%A Sundaram, Suresh
%A Ramasamy, Savitha
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F gautam-etal-2022-refinement
%X Zero-Shot Learning (ZSL) has shown great promise at the intersection of vision and language, and generative methods for ZSL are predominant owing to their efficiency. Moreover, textual description or attribute plays a critical role in transferring knowledge from the seen to unseen classes in ZSL. Such generative approaches for ZSL are very costly to train and require the class description of the unseen classes during training. In this work, we propose a non-generative gating-based attribute refinement network for ZSL, which achieves similar accuracies to generative methods of ZSL, at a much lower computational cost. The refined attributes are mapped into the visual domain through an attribute embedder, and the whole network is guided by the circle loss and the well-known softmax cross-entropy loss to obtain a robust class embedding. We refer to our approach as Circle loss guided gating-based Attribute-Refinement Network (CARNet). We perform extensive experiments on the five benchmark datasets over the various challenging scenarios viz., Generalized ZSL (GZSL), Continual GZSL (CGZSL), and conventional ZSL. We observe that the CARNet significantly outperforms recent non-generative ZSL methods and most generative ZSL methods in all three settings by a significant margin. Our extensive ablation study disentangles the performance of various components and justifies their importance. The source code is available at https://github.com/Sethup123/CARNet.
%R 10.18653/v1/2022.findings-emnlp.455
%U https://aclanthology.org/2022.findings-emnlp.455
%U https://doi.org/10.18653/v1/2022.findings-emnlp.455
%P 6127-6140
Markdown (Informal)
[Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning](https://aclanthology.org/2022.findings-emnlp.455) (Gautam et al., Findings 2022)
ACL