{"id":"https://openalex.org/W7155083649","doi":"https://doi.org/10.1109/icassp55912.2026.11462541","title":"DeepTraverse: An Algorithm-Inspired Design Paradigm for Structured and Interpretable Vision Backbones","display_name":"DeepTraverse: An Algorithm-Inspired Design Paradigm for Structured and Interpretable Vision Backbones","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155083649","doi":"https://doi.org/10.1109/icassp55912.2026.11462541"},"language":"en","primary_location":{"id":"doi:10.1109/icassp55912.2026.11462541","doi":"https://doi.org/10.1109/icassp55912.2026.11462541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462541","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101666012","display_name":"Bin Guo","orcid":"https://orcid.org/0009-0001-7972-1833","observed_orcids":["https://orcid.org/0009-0001-7972-1833"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Guo","raw_affiliation_strings":["University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24563799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1606","last_page":"1610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretable-neural-networks","display_name":"interpretable neural networks","score":0.6539999842643738},{"id":"https://openalex.org/keywords/feature-salience","display_name":"feature saliency","score":0.7450000047683716},{"id":"https://openalex.org/keywords/saliency-maps","display_name":"saliency maps","score":0.8899999856948853},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.7009999752044678},{"id":"https://openalex.org/keywords/weight-sharing","display_name":"parameter sharing","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116000175476074},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23430000245571136},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.23340000212192535},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.23199999332427979},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.23180000483989716}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp55912.2026.11462541","doi":"https://doi.org/10.1109/icassp55912.2026.11462541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462541","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2534652523","https://openalex.org/W2883780447","https://openalex.org/W2941717673","https://openalex.org/W2944779197","https://openalex.org/W2963446712","https://openalex.org/W2964137095","https://openalex.org/W3035414587","https://openalex.org/W4386047745","https://openalex.org/W4392903135","https://openalex.org/W4396712645","https://openalex.org/W4402727675","https://openalex.org/W4408697023","https://openalex.org/W4411173625","https://openalex.org/W4415797951"],"related_works":["https://openalex.org/W4417347754","https://openalex.org/W7141267860","https://openalex.org/W7128729036","https://openalex.org/W4399366442","https://openalex.org/W4416359369","https://openalex.org/W7172434066","https://openalex.org/W3034514369","https://openalex.org/W4312323989","https://openalex.org/W4226436274","https://openalex.org/W3012287122"],"abstract_inverted_index":{"Although":[0],"conventional":[1],"vision":[2,46],"backbones":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7,12],"on":[8,16,98,103],"benchmark":[9],"datasets,":[10],"their":[11],"improvements":[13],"often":[14],"rely":[15],"increasing":[17],"model":[18],"size,":[19],"which":[20],"is":[21],"a":[22,72,89,123],"strategy":[23],"that":[24,57,76,92,107],"lacks":[25],"architectural":[26],"clarity":[27],"and":[28,44,125],"interpretability.":[29],"This":[30],"study":[31],"explores":[32],"whether":[33],"prior":[34],"algorithmic":[35],"knowledge":[36],"can":[37],"guide":[38],"the":[39],"design":[40],"of":[41],"more":[42,126],"interpretable":[43,64],"efficient":[45],"backbones.":[47],"To":[48],"this":[49],"end,":[50],"we":[51],"propose":[52],"DeepTraverse,":[53],"an":[54],"algorithm-inspired":[55],"architecture":[56],"incorporates":[58],"structured":[59],"control":[60],"flow":[61],"to":[62],"produce":[63],"representations.":[65],"Its":[66],"primary":[67],"components":[68],"are":[69],"twofold.":[70],"First,":[71],"recursive":[73],"exploration":[74],"module":[75,91],"deepens":[77],"feature":[78,95],"analysis":[79],"along":[80],"promising":[81],"paths":[82],"while":[83,114],"sharing":[84],"parameters":[85],"for":[86],"efficiency.":[87],"Second,":[88],"backtracking":[90],"adaptively":[93],"recalibrates":[94],"salience":[96],"based":[97],"evolving":[99],"global":[100],"context.":[101],"Experiments":[102],"standard":[104],"benchmarks":[105],"demonstrate":[106,122],"DeepTraverse":[108],"surpasses":[109],"competitive":[110],"baselines":[111],"in":[112],"accuracy":[113],"reducing":[115],"computational":[116],"cost.":[117],"Furthermore,":[118],"its":[119],"saliency":[120],"maps":[121],"sharper":[124],"task-relevant":[127],"localization.":[128]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-22T00:00:00"}