Sparse Hyperspectral Band Selection Based on Expectation Maximization
Hyperspectral band selection seeks to identify a compact subset of informative spectral channels that preserves task-relevant information while mitigating the storage, transmission, and computational burdens imposed by high-dimensional data. Yet prevailing techniques face two pervasive limitations:...
Uložené v:
| Vydané v: | IEEE transactions on circuits and systems for video technology s. 1 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
2025
|
| Predmet: | |
| ISSN: | 1051-8215, 1558-2205 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Hyperspectral band selection seeks to identify a compact subset of informative spectral channels that preserves task-relevant information while mitigating the storage, transmission, and computational burdens imposed by high-dimensional data. Yet prevailing techniques face two pervasive limitations: (i) scoring- or ranking-based methods assess bands independently, overlooking the joint dependency that determine their true utility; and (ii) combinatorial search approaches, though theoretically exhaustive, require prohibitive enumeration that is incompatible with the scale and end-to-end nature of modern deep-learning pipelines. We recast band selection as a combinatorial inference problem and propose a task-agnostic framework that embeds a learnable Band Selection Layer equipped with an Expectation-Maximization-driven Sparsity Loss The E-step efficiently enumerates the expected likelihood of all k -out-of- B band subsets via dynamic programming, thereby making implicit dependencies explicit; the M-step optimises band importances toward a provably k -sparse solution without post-hoc thresholding. Comprehensive theoretical analysis proves the absence of spurious local maxima and guarantees convergence to an exact sparse optimum. Extensive experiments on three public benchmarks (KSC, HT2013, HT2018), two auxiliary tasks (anomaly and target detection), and six classifiers demonstrate that the proposed method consistently surpasses state-of-the-art baselines. The results confirm that EM-guided sparsification not only stabilises the sparsity pattern but also yields interpretable inter-band dependency structures, making the framework a robust and broadly applicable tool for hyperspectral analysis and other sparsity-oriented vision problems. |
|---|---|
| AbstractList | Hyperspectral band selection seeks to identify a compact subset of informative spectral channels that preserves task-relevant information while mitigating the storage, transmission, and computational burdens imposed by high-dimensional data. Yet prevailing techniques face two pervasive limitations: (i) scoring- or ranking-based methods assess bands independently, overlooking the joint dependency that determine their true utility; and (ii) combinatorial search approaches, though theoretically exhaustive, require prohibitive enumeration that is incompatible with the scale and end-to-end nature of modern deep-learning pipelines. We recast band selection as a combinatorial inference problem and propose a task-agnostic framework that embeds a learnable Band Selection Layer equipped with an Expectation-Maximization-driven Sparsity Loss The E-step efficiently enumerates the expected likelihood of all k -out-of- B band subsets via dynamic programming, thereby making implicit dependencies explicit; the M-step optimises band importances toward a provably k -sparse solution without post-hoc thresholding. Comprehensive theoretical analysis proves the absence of spurious local maxima and guarantees convergence to an exact sparse optimum. Extensive experiments on three public benchmarks (KSC, HT2013, HT2018), two auxiliary tasks (anomaly and target detection), and six classifiers demonstrate that the proposed method consistently surpasses state-of-the-art baselines. The results confirm that EM-guided sparsification not only stabilises the sparsity pattern but also yields interpretable inter-band dependency structures, making the framework a robust and broadly applicable tool for hyperspectral analysis and other sparsity-oriented vision problems. |
| Author | Xue, Xinhui Gao, Likun Zheng, Haowen |
| Author_xml | – sequence: 1 givenname: Likun orcidid: 0000-0001-5191-5890 surname: Gao fullname: Gao, Likun organization: Beijing Key Laboratory of Digital Media School of Computer Science and Engineering, Beihang University, Beijing, China – sequence: 2 givenname: Xinhui orcidid: 0000-0003-1439-9107 surname: Xue fullname: Xue, Xinhui organization: Beijing Key Laboratory of Digital Media School of Computer Science and Engineering, Beihang University, Beijing, China – sequence: 3 givenname: Haowen surname: Zheng fullname: Zheng, Haowen organization: Beijing Key Laboratory of Digital Media School of Computer Science and Engineering, Beihang University, Beijing, China |
| BookMark | eNpFkE9PwkAQxTcGEwH9AsZDv0BxZne23R6VIJhgPIBem6HMJjVQml0O4Ke3_Ek8zXuTeZOX30D1ml0jSj0ijBCheF6OF9_LkQZtR8YWeQZ0o_porUu1BtvrNFhMnUZ7pwYx_gAgOcr7arJoOURJZsdWQmyl2gfeJK_crJOFbDpb75rORlknnZgcThd8Xn7wod7Wv2dzr249b6I8XOdQfb1NluNZOv-cvo9f5mmFJtunxjET0DpzaJiEqOsgxDlnAKbyjitbUe4LKXhV0IrsynkhlxGSyZ33Zqj05W8VdjEG8WUb6i2HY4lQnkCUZxDlCUR5BdGFni6hWkT-A4haW8jMH_BJXGY |
| CODEN | ITCTEM |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION |
| DOI | 10.1109/TCSVT.2025.3597604 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 1 |
| ExternalDocumentID | 10_1109_TCSVT_2025_3597604 11122506 |
| Genre | orig-research |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 5VS AAYXX AETIX AGSQL AI. AIBXA ALLEH CITATION EJD H~9 ICLAB IFJZH VH1 |
| ID | FETCH-LOGICAL-c136t-38aa404d6813a4e44484e4a7a6003cf8ac5c47f9e9ab94b45b8fe486414378ff3 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Sat Nov 29 07:38:31 EST 2025 Wed Aug 27 01:43:18 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c136t-38aa404d6813a4e44484e4a7a6003cf8ac5c47f9e9ab94b45b8fe486414378ff3 |
| ORCID | 0000-0003-1439-9107 0000-0001-5191-5890 |
| PageCount | 1 |
| ParticipantIDs | ieee_primary_11122506 crossref_primary_10_1109_TCSVT_2025_3597604 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-00-00 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 2025-00-00 |
| PublicationDecade | 2020 |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0014847 |
| Score | 2.4582953 |
| Snippet | Hyperspectral band selection seeks to identify a compact subset of informative spectral channels that preserves task-relevant information while mitigating the... |
| SourceID | crossref ieee |
| SourceType | Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Clustering algorithms Computational efficiency Computational modeling Correlation EM algorithm Encoding Faces Hyperspectral band selection hyperspectral image classification Hyperspectral imaging Redundancy sparse learning Training Transformers |
| Title | Sparse Hyperspectral Band Selection Based on Expectation Maximization |
| URI | https://ieeexplore.ieee.org/document/11122506 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2205 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014847 issn: 1051-8215 databaseCode: RIE dateStart: 19910101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYoCBZxHlpQxsyG2CL36MULXqABVSC-oWOY4jdSCt-kD8fM6OC10YWCInsqXoO1u-8_m7j5A75WTiSiMpgzymoEVC8zhn1EicHUJLmdYl85_FcCgnE_UayOqeC2Ot9ZfPbNs1fS6_mJm1Oyrr4LrE6ecKbO8KwWuy1k_KAKRXE0N_IaESN7INQyZWnXF39D7GWPAhbTN0oHlQZdvsQluyKn5X6R_983-OyWFwH6PH2t4nZMdWp-Rgq6jgGemN5his2miAEWZNpFzgiCddFdHIi96gJfB1aYsIG67UsanT8dGL_pp-BF5mk7z1e-PugAaxBGoSxleUSa0hhoLLhGmwgGEXPrXQ6NEwU0ptUgOiVFbpXEEOaS5LC5IDOkxCliU7J41qVtkLEknsDWnh1zLYXGqecJNAohRasORxi9xvwMvmdU2MzMcSsco81JmDOgtQt0jTIffbM4B2-cf3K7LvhtfHHNeksVqs7Q3ZM5-r6XJx623-Dce6qGo |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZQQQIGnkWUZwY25DbBTnIeoWpVRFshNaBukeM4UgfSqg_Ez-fsuNCFgSVyIieyvrPlO1---wi5E0YmrlBAGc98ymUc0MzPGFWAsyOWAGFVMr8fD4cwHotXR1a3XBittf35TDdN0-by86lamaOyFq5LnH6mwPa2kc5ydK2fpAEHqyeGHkNAAbeyNUfGF62kPXpPMBp8CJsMXejI6bKt96ENYRW7r3QP_zmiI3LgHEjvsbL4MdnS5QnZ3ygreEo6oxmGq9rrYYxZUSnn-MaTLHNvZGVv0BZ4u9C5hw1T7FhVCXlvIL8mH46ZWSdv3U7S7lEnl0BVwKIlZSAl93keQcAk1xwDL7zKWKJPw1QBUoWKx4XQQmaCZzzMoNAcIo4uUwxFwc5IrZyW-px4gL15mNvVzHUGMgoiFfBACLRhEfkNcr8GL51VVTFSG034IrVQpwbq1EHdIHWD3G9PB9rFH89vyW4vGfTT_vPw5ZLsmU9Vhx5XpLacr_Q12VGfy8lifmPt_w3AKKuz |
| 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%3Ajournal&rft.genre=article&rft.atitle=Sparse+Hyperspectral+Band+Selection+Based+on+Expectation+Maximization&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Gao%2C+Likun&rft.au=Xue%2C+Xinhui&rft.au=Zheng%2C+Haowen&rft.date=2025&rft.pub=IEEE&rft.issn=1051-8215&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTCSVT.2025.3597604&rft.externalDocID=11122506 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |