Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning.
Saved in:
| Title: | Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning. |
|---|---|
| Authors: | Chen, Tianshui1 tianshuichen@gmail.com, Pu, Tao2 putao3@mail2.sysu.edu.cn, Wu, Hefeng2 wuhefeng@mail.sysu.edu.cn, Xie, Yuan2 phoenixsysu@gmail.com, Liu, Lingbo3 lingbo.liu@polyu.edu.hk, Lin, Liang2 linliang@ieee.org |
| Source: | IEEE Transactions on Pattern Analysis & Machine Intelligence. Dec2022, Vol. 44 Issue Part3, p9887-9903. 17p. |
| Subjects: | Facial expression, Representations of graphs, Distribution (Probability theory), Learning ability |
| Abstract: | Facial expression recognition (FER) has received significant attention in the past decade with witnessed progress, but data inconsistencies among different FER datasets greatly hinder the generalization ability of the models learned on one dataset to another. Recently, a series of cross-domain FER algorithms (CD-FERs) have been extensively developed to address this issue. Although each declares to achieve superior performance, comprehensive and fair comparisons are lacking due to inconsistent choices of the source/target datasets and feature extractors. In this work, we first propose to construct a unified CD-FER evaluation benchmark, in which we re-implement the well-performing CD-FER and recently published general domain adaptation algorithms and ensure that all these algorithms adopt the same source/target datasets and feature extractors for fair CD-FER evaluations. Based on the analysis, we find that most of the current state-of-the-art algorithms use adversarial learning mechanisms that aim to learn holistic domain-invariant features to mitigate domain shifts. However, these algorithms ignore local features, which are more transferable across different datasets and carry more detailed content for fine-grained adaptation. Therefore, we develop a novel adversarial graph representation adaptation (AGRA) framework that integrates graph representation propagation with adversarial learning to realize effective cross-domain holistic-local feature co-adaptation. Specifically, our framework first builds two graphs to correlate holistic and local regions within each domain and across different domains, respectively. Then, it extracts holistic-local features from the input image and uses learnable per-class statistical distributions to initialize the corresponding graph nodes. Finally, two stacked graph convolution networks (GCNs) are adopted to propagate holistic-local features within each domain to explore their interaction and across different domains for holistic-local feature co-adaptation. In this way, the AGRA framework can adaptively learn fine-grained domain-invariant features and thus facilitate cross-domain expression recognition. We conduct extensive and fair comparisons on the unified evaluation benchmark and show that the proposed AGRA framework outperforms previous state-of-the-art methods. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Transactions on Pattern Analysis & Machine Intelligence is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 160711826 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chen%2C+Tianshui%22">Chen, Tianshui</searchLink><relatesTo>1</relatesTo><i> tianshuichen@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Pu%2C+Tao%22">Pu, Tao</searchLink><relatesTo>2</relatesTo><i> putao3@mail2.sysu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Hefeng%22">Wu, Hefeng</searchLink><relatesTo>2</relatesTo><i> wuhefeng@mail.sysu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Xie%2C+Yuan%22">Xie, Yuan</searchLink><relatesTo>2</relatesTo><i> phoenixsysu@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Lingbo%22">Liu, Lingbo</searchLink><relatesTo>3</relatesTo><i> lingbo.liu@polyu.edu.hk</i><br /><searchLink fieldCode="AR" term="%22Lin%2C+Liang%22">Lin, Liang</searchLink><relatesTo>2</relatesTo><i> linliang@ieee.org</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Pattern+Analysis+%26+Machine+Intelligence%22">IEEE Transactions on Pattern Analysis & Machine Intelligence</searchLink>. Dec2022, Vol. 44 Issue Part3, p9887-9903. 17p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Facial+expression%22">Facial expression</searchLink><br /><searchLink fieldCode="DE" term="%22Representations+of+graphs%22">Representations of graphs</searchLink><br /><searchLink fieldCode="DE" term="%22Distribution+%28Probability+theory%29%22">Distribution (Probability theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Learning+ability%22">Learning ability</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Facial expression recognition (FER) has received significant attention in the past decade with witnessed progress, but data inconsistencies among different FER datasets greatly hinder the generalization ability of the models learned on one dataset to another. Recently, a series of cross-domain FER algorithms (CD-FERs) have been extensively developed to address this issue. Although each declares to achieve superior performance, comprehensive and fair comparisons are lacking due to inconsistent choices of the source/target datasets and feature extractors. In this work, we first propose to construct a unified CD-FER evaluation benchmark, in which we re-implement the well-performing CD-FER and recently published general domain adaptation algorithms and ensure that all these algorithms adopt the same source/target datasets and feature extractors for fair CD-FER evaluations. Based on the analysis, we find that most of the current state-of-the-art algorithms use adversarial learning mechanisms that aim to learn holistic domain-invariant features to mitigate domain shifts. However, these algorithms ignore local features, which are more transferable across different datasets and carry more detailed content for fine-grained adaptation. Therefore, we develop a novel adversarial graph representation adaptation (AGRA) framework that integrates graph representation propagation with adversarial learning to realize effective cross-domain holistic-local feature co-adaptation. Specifically, our framework first builds two graphs to correlate holistic and local regions within each domain and across different domains, respectively. Then, it extracts holistic-local features from the input image and uses learnable per-class statistical distributions to initialize the corresponding graph nodes. Finally, two stacked graph convolution networks (GCNs) are adopted to propagate holistic-local features within each domain to explore their interaction and across different domains for holistic-local feature co-adaptation. In this way, the AGRA framework can adaptively learn fine-grained domain-invariant features and thus facilitate cross-domain expression recognition. We conduct extensive and fair comparisons on the unified evaluation benchmark and show that the proposed AGRA framework outperforms previous state-of-the-art methods. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Transactions on Pattern Analysis & Machine Intelligence is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=160711826 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TPAMI.2021.3131222 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 9887 Subjects: – SubjectFull: Facial expression Type: general – SubjectFull: Representations of graphs Type: general – SubjectFull: Distribution (Probability theory) Type: general – SubjectFull: Learning ability Type: general Titles: – TitleFull: Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chen, Tianshui – PersonEntity: Name: NameFull: Pu, Tao – PersonEntity: Name: NameFull: Wu, Hefeng – PersonEntity: Name: NameFull: Xie, Yuan – PersonEntity: Name: NameFull: Liu, Lingbo – PersonEntity: Name: NameFull: Lin, Liang IsPartOfRelationships: – BibEntity: Dates: – D: 30 M: 12 Text: Dec2022 Type: published Y: 2022 Identifiers: – Type: issn-print Value: 01628828 Numbering: – Type: volume Value: 44 – Type: issue Value: Part3 Titles: – TitleFull: IEEE Transactions on Pattern Analysis & Machine Intelligence Type: main |
| ResultId | 1 |
