{"id":"https://openalex.org/W7160941160","doi":"https://doi.org/10.48550/arxiv.2605.08193","title":"Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising","display_name":"Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160941160","doi":"https://doi.org/10.48550/arxiv.2605.08193"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08193","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08193","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.08193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088490405","display_name":"Youssef Saied","orcid":"https://orcid.org/0000-0002-4033-6022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saied, Youssef","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135949713","display_name":"Fran\u00e7ois Fleuret","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fleuret, Fran\u00e7ois","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.20340000092983246,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.20340000092983246,"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/T11019","display_name":"Image Enhancement Techniques","score":0.10379999876022339,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0925000011920929,"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/normalization","display_name":"Normalization (sociology)","score":0.6510999798774719},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6190000176429749},{"id":"https://openalex.org/keywords/brightness","display_name":"Brightness","score":0.3653999865055084},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.35910001397132874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33219999074935913},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.32749998569488525}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6510999798774719},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6190000176429749},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5566999912261963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241000056266785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41290000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C151596937","wikidata":"https://www.wikidata.org/wiki/Q856980","display_name":"Bidirectional reflectance distribution function","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08193","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08193","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.08193","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08193","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Normalization":[0,66],"Equivariance":[1,67],"(NE)":[2],"is":[3,19],"a":[4,28,69],"structural":[5],"prior":[6],"that":[7,72],"improves":[8,109],"robustness":[9,110],"to":[10,44,125],"distribution":[11],"shift":[12],"in":[13],"image-to-image":[14],"tasks.":[15],"A":[16],"function":[17,87],"$f$":[18],"normalization":[20],"equivariant":[21],"iff":[22],"$f(a":[23],"y":[24],"+":[25,30],"b\\mathbf{1})":[26],"=":[27],"f(y)":[29],"b\\mathbf{1}$":[31],"for":[32],"all":[33],"$a>0$":[34],"and":[35,52,61,79,106],"$b\\in\\mathbb{R}$.":[36],"Existing":[37],"NE":[38,86,99,121],"methods":[39],"constrain":[40],"every":[41,85],"internal":[42],"layer":[43],"NE-compatible":[45],"operations.":[46],"These":[47],"constraints":[48],"add":[49],"runtime":[50],"cost":[51],"exclude":[53],"standard":[54],"transformer":[55,107],"components":[56],"such":[57],"as":[58],"softmax":[59],"attention":[60],"LayerNorm.":[62],"We":[63,83],"introduce":[64],"Wrapped":[65],"(WNE),":[68],"parameter-free":[70],"wrapper":[71,93],"normalizes":[73],"the":[74,81,92,96],"input,":[75],"applies":[76],"any":[77],"backbone,":[78],"denormalizes":[80],"output.":[82],"prove":[84],"admits":[88],"this":[89],"factorization,":[90],"so":[91],"exactly":[94],"parameterizes":[95],"class":[97],"of":[98],"functions.":[100],"On":[101],"blind":[102],"denoising,":[103],"wrapping":[104],"CNN":[105],"architectures":[108],"under":[111],"noise-level":[112],"mismatch":[113],"with":[114],"no":[115],"measurable":[116],"GPU":[117],"overhead,":[118],"while":[119],"architectural":[120],"baselines":[122],"are":[123],"up":[124],"$1.6\\times$":[126],"slower.":[127]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}