{"id":"https://openalex.org/W4416243768","doi":"https://doi.org/10.1109/iccv51701.2025.02076","title":"Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment","display_name":"Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416243768","doi":"https://doi.org/10.1109/iccv51701.2025.02076"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.08811","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103326014","display_name":"Shichen Zhang","orcid":"https://orcid.org/0009-0007-1973-306X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Chen Zhang","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041840208","display_name":"Yunheng Li","orcid":"https://orcid.org/0000-0003-2298-0540"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunheng Li","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001598042","display_name":"Yu-Huan Wu","orcid":"https://orcid.org/0000-0001-8666-3435"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yu-Huan Wu","raw_affiliation_strings":["IHPC, A*STAR,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IHPC, A*STAR,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040392623","display_name":"Qibin Hou","orcid":"https://orcid.org/0000-0002-8388-8708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibin Hou","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22361","last_page":"22371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9031999707221985,"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":0.9031999707221985,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.019700000062584877,"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":0.015300000086426735,"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/inference","display_name":"Inference","score":0.6554999947547913},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6402000188827515},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5845999717712402},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5339999794960022},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43320000171661377},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4250999987125397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833000183105469},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4011000096797943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37770000100135803},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.08811","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08811","pdf_url":"https://arxiv.org/pdf/2508.08811","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.08811","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.08811","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.08811","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08811","pdf_url":"https://arxiv.org/pdf/2508.08811","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,116],"is":[2],"fundamental":[3],"to":[4,96,127],"vision":[5],"systems":[6],"requiring":[7],"pixel-level":[8],"scene":[9],"understanding,":[10],"yet":[11],"deploying":[12],"it":[13],"on":[14,107,137,155],"resource-constrained":[15],"devices":[16],"demands":[17],"efficient":[18,62,114],"architectures.":[19],"Although":[20],"existing":[21,128],"methods":[22,129],"achieve":[23],"real-time":[24],"inference":[25],"through":[26],"lightweight":[27],"designs,":[28],"we":[29,50,81,111],"reveal":[30],"their":[31],"inherent":[32],"limitation:":[33],"misalignment":[34],"between":[35],"class":[36,94,100],"representations":[37,101],"and":[38,93,102,144,167,172],"image":[39,104],"features":[40,66],"caused":[41],"by":[42,169],"a":[43,57,83],"per-pixel":[44],"classification":[45],"paradigm.":[46],"With":[47],"experimental":[48],"analysis,":[49],"find":[51],"that":[52,89],"this":[53,79],"paradigm":[54,88,123,163],"results":[55],"in":[56,74],"highly":[58],"challenging":[59],"assumption":[60],"for":[61,70],"scenarios:":[63],"Image":[64],"pixel":[65],"should":[67],"not":[68],"vary":[69],"the":[71,108,120,156],"same":[72],"category":[73],"different":[75],"images.":[76],"To":[77],"address":[78],"dilemma,":[80],"propose":[82],"coupled":[84],"dual-branch":[85],"offset":[86,121,161],"learning":[87,122,162],"explicitly":[90],"learns":[91],"feature":[92],"offsets":[95],"dynamically":[97],"refine":[98],"both":[99],"spatial":[103],"features.":[105],"Based":[106],"proposed":[109,160],"paradigm,":[110],"construct":[112],"an":[113],"semantic":[115],"network,":[117],"OffSeg.":[118],"Notably,":[119],"can":[124],"be":[125],"adopted":[126],"with":[130,150,176],"no":[131],"additional":[132,179],"architectural":[133],"changes.":[134],"Extensive":[135],"experiments":[136],"four":[138],"datasets,":[139],"including":[140],"ADE20K,":[141],"Cityscapes,":[142],"COCO-Stuff-164K,":[143],"Pascal":[145],"Context,":[146],"demonstrate":[147],"consistent":[148],"improvements":[149],"negligible":[151],"parameters.":[152],"For":[153],"instance,":[154],"ADE20K":[157],"dataset,":[158],"our":[159],"improves":[164],"SegFormer-B0,":[165],"SegNeXt-T,":[166],"Mask2Former-Tiny":[168],"2.7%,":[170],"1.9%,":[171],"2.6%":[173],"mIoU,":[174],"respectively,":[175],"only":[177],"0.1-0.2M":[178],"parameters":[180],"required.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}