Frequency-Aware Hierarchical Image Compression for Humans and Machines
To achieve efficient compression for both human vision and machine perception, scalable coding methods have been proposed in recent years. However, existing methods do not fully eliminate the redundancy between features corresponding to different tasks, resulting in suboptimal coding performance. In...
Uložené v:
| Vydané v: | Visual communications and image processing (Online) s. 1 - 5 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
08.12.2024
|
| Predmet: | |
| ISSN: | 2642-9357 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | To achieve efficient compression for both human vision and machine perception, scalable coding methods have been proposed in recent years. However, existing methods do not fully eliminate the redundancy between features corresponding to different tasks, resulting in suboptimal coding performance. In this paper, we propose a frequency-aware hierarchical image compression framework designed for humans and machines. Specifically, we investigate task relationships from a frequency perspective, utilizing only HF information for machine vision tasks and leveraging both HF and LF features for image reconstruction. Besides, the residual block embedded octave convolution module is designed to enhance the information interaction between HF features and LF features. Additionally, a dual-frequency channel-wise entropy model is applied to reasonably exploit the correlation between different tasks, thereby improving multi-task performance. The experiments show that the proposed method offers -69.3%∼-75.3% coding gains on machine vision tasks compared to the relevant benchmarks, and -19.1% gains over state-of-the-art scalable image codec in terms of image reconstruction quality. |
|---|---|
| AbstractList | To achieve efficient compression for both human vision and machine perception, scalable coding methods have been proposed in recent years. However, existing methods do not fully eliminate the redundancy between features corresponding to different tasks, resulting in suboptimal coding performance. In this paper, we propose a frequency-aware hierarchical image compression framework designed for humans and machines. Specifically, we investigate task relationships from a frequency perspective, utilizing only HF information for machine vision tasks and leveraging both HF and LF features for image reconstruction. Besides, the residual block embedded octave convolution module is designed to enhance the information interaction between HF features and LF features. Additionally, a dual-frequency channel-wise entropy model is applied to reasonably exploit the correlation between different tasks, thereby improving multi-task performance. The experiments show that the proposed method offers -69.3%∼-75.3% coding gains on machine vision tasks compared to the relevant benchmarks, and -19.1% gains over state-of-the-art scalable image codec in terms of image reconstruction quality. |
| Author | Yu, Li Kuang, Jinhao Zhang, Zixiang Luo, Yue |
| Author_xml | – sequence: 1 givenname: Yue surname: Luo fullname: Luo, Yue organization: Huazhong University of Science and Technology,Wuhan,China – sequence: 2 givenname: Zixiang surname: Zhang fullname: Zhang, Zixiang organization: Huazhong University of Science and Technology,Wuhan,China – sequence: 3 givenname: Jinhao surname: Kuang fullname: Kuang, Jinhao organization: Huazhong University of Science and Technology,Wuhan,China – sequence: 4 givenname: Li surname: Yu fullname: Yu, Li email: hustlyu@hust.edu.cn organization: Huazhong University of Science and Technology,Wuhan,China |
| BookMark | eNo1j9FKwzAYRqMoOGffQDAv0JrkT9PkchRrCxO9UG9Hmv7VyJrOxCF7ewfq1XdzOJzvkpyFOSAhN5wVnDNz-1p3Twq4YoVgQhacaWm0qU5IZiqjAXgpTCnhlCyEkiI3UFYXJEvpgzEmSg7C6AVpmoifewzukK--bUTaeow2unfv7JZ2k31DWs_TLmJKfg50nCNt95MNidow0Ad7JAOmK3I-2m3C7G-X5KW5e67bfP1439Wrde45U1-5HGQJqKpeycGA1urYZK1AC6OqpOmFq5xjemSDNoL3XGk2KNlrECgAtYEluf71ekTc7KKfbDxs_q_DD_rxTq8 |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/VCIP63160.2024.10849897 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 9798331529543 |
| EISSN | 2642-9357 |
| EndPage | 5 |
| ExternalDocumentID | 10849897 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IF 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK M43 OCL RIE RIL |
| ID | FETCH-LOGICAL-i106t-4d453e67b64d93886357aa2ea3f6749b2c7cc08f0d8921b1680d64b832e23e893 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001431710700096&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Feb 12 06:22:40 EST 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i106t-4d453e67b64d93886357aa2ea3f6749b2c7cc08f0d8921b1680d64b832e23e893 |
| PageCount | 5 |
| ParticipantIDs | ieee_primary_10849897 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-Dec.-8 |
| PublicationDateYYYYMMDD | 2024-12-08 |
| PublicationDate_xml | – month: 12 year: 2024 text: 2024-Dec.-8 day: 08 |
| PublicationDecade | 2020 |
| PublicationTitle | Visual communications and image processing (Online) |
| PublicationTitleAbbrev | VCIP |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0002513298 |
| Score | 2.2764351 |
| Snippet | To achieve efficient compression for both human vision and machine perception, scalable coding methods have been proposed in recent years. However, existing... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Codecs Convolution Correlation Entropy Image coding image coding for machines Image reconstruction learned image compression Machine vision Multitasking Redundancy scalable image coding Visual communication |
| Title | Frequency-Aware Hierarchical Image Compression for Humans and Machines |
| URI | https://ieeexplore.ieee.org/document/10849897 |
| WOSCitedRecordID | wos001431710700096&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVoxcBUPor4lgdWlyR2YntEFVE7UGUA1K1y7LNUCVKUtCD-PbaTFjEwsFmWLFln3d3z-T0fQrepw0CxNZRwYIwwmyakdDiBaC9FSFOblJaFZhN8NhPzuSw6sXrQwgBAIJ_ByA_DW75Z6Y0vlTkPF0wKyXuox3nWirV2BRWXqGkiRcfhiiN59zKeFhn15RN3w2ej7epffVRCGskH_9zAIRr-CPJwsUs1R2gPqmM06BAk7vyzOUF5XrfU6C9y_6lqwJOlFxiHfievePrmggf2EaAlv1bYIVYcyvgNVpXBj4FZCc0QPecPT-MJ6TolkKW70q0JMyylkPEyY0ZSIfwnc0oloKjNOJNlornWkbCRETKJyzgTkclY6bwZEgoOspyifrWq4AxhsNyUTFijGfWvnsplOa2twwlacWqjczT0dlm8t59hLLYmufhj_hIdeOsHBoi4Qv11vYFrtK8_1sumvglH-A3e65ut |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT3VR8W3OXhN3U2ym-QoxaXFtvRQpbeSzQMKupXdVvHfm2S3igcP3kIgECZM5pvJ92UAuE0cBoqtJogZShG1CUa5wwlIeSlCklicWxqaTbDxmM9mYtKI1YMWxhgTyGem64fhLV8v1dqXypyHcyq4YNtgJ6EUR7Vc67uk4kI1wYI3LK44EnfPvcEkJb6A4nJ82t2s_9VJJQSSrP3PLRyAzo8kD06-g80h2DLFEWg3GBI2Hlodgywra3L0J7r_kKWB_YWXGIeOJy9w8OquD-jvgJr-WkCHWWEo5FdQFhqOArfSVB3wlD1Me33U9EpAC5fUrRDVNCEmZXlKtSCc-2_mpMRGEpsyKnKsmFIRt5HmAsd5nPJIpzR3_mwwMQ60nIBWsSzMKYDGMp1TbrWixL97ShfnlLIOKSjJiI3OQMfbZf5Wf4cx35jk_I_5G7DXn46G8-Fg_HgB9v1JBD4IvwStVbk2V2BXva8WVXkdjvMLKRue9A |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Visual+communications+and+image+processing+%28Online%29&rft.atitle=Frequency-Aware+Hierarchical+Image+Compression+for+Humans+and+Machines&rft.au=Luo%2C+Yue&rft.au=Zhang%2C+Zixiang&rft.au=Kuang%2C+Jinhao&rft.au=Yu%2C+Li&rft.date=2024-12-08&rft.pub=IEEE&rft.eissn=2642-9357&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FVCIP63160.2024.10849897&rft.externalDocID=10849897 |