{"id":"https://openalex.org/W7148724279","doi":"https://doi.org/10.48550/arxiv.2604.01843","title":"Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images","display_name":"Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148724279","doi":"https://doi.org/10.48550/arxiv.2604.01843"},"language":"en","primary_location":{"id":"pmh:oai:durham-repository.worktribe.com:5257374","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/5257374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://durham-repository.worktribe.com/output/5257374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132867806","display_name":"Jamie S. J. Stirling","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stirling, Jamie S. J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091886479","display_name":"Noura Al-Moubayed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Al-Moubayed, Noura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038258635","display_name":"Hubert P. H. Shum","orcid":"https://orcid.org/0000-0001-5651-6039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shum, Hubert P. H.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132867806"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.671500027179718,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.671500027179718,"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/T11448","display_name":"Face recognition and analysis","score":0.11270000040531158,"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":0.06369999796152115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6373999714851379},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.5339999794960022},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5310999751091003},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5171999931335449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45399999618530273},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4375999867916107},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.43389999866485596},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4185999929904938},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.398499995470047}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6373999714851379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5480999946594238},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.5339999794960022},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5171999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48159998655319214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.398499995470047},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3962000012397766},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36719998717308044},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.25209999084472656},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:durham-repository.worktribe.com:5257374","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/5257374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},{"id":"doi:10.48550/arxiv.2604.01843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01843","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":"article"}],"best_oa_location":{"id":"pmh:oai:durham-repository.worktribe.com:5257374","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/5257374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vector":[0],"quantization":[1,108],"approaches":[2],"(VQ-VAE,":[3],"VQ-GAN)":[4],"learn":[5],"discrete":[6,47],"neural":[7],"representations":[8,13,48],"of":[9,49,99,130,140,181],"images,":[10],"but":[11],"these":[12],"are":[14,18,64],"inherently":[15],"position-dependent:":[16],"codes":[17,63,77,133],"spatially":[19,50],"arranged":[20],"and":[21,83,154,160,179],"contextually":[22],"entangled,":[23],"requiring":[24],"autoregressive":[25],"or":[26],"diffusion-based":[27],"priors":[28],"to":[29,66,78,123,174,186],"model":[30],"their":[31],"dependencies":[32],"at":[33],"sample":[34],"time.":[35],"In":[36],"this":[37,74],"work,":[38],"we":[39,102],"ask":[40],"whether":[41],"positional":[42,69],"information":[43,97],"is":[44],"necessary":[45],"for":[46,163,189],"aligned":[51],"data.":[52],"We":[53,71,148,169],"propose":[54],"the":[55,95,131,171,182],"permutation-invariant":[56,100],"vector-quantized":[57],"autoencoder":[58],"(PI-VQ),":[59],"in":[60,143],"which":[61],"latent":[62,183],"constrained":[65],"carry":[67],"no":[68],"information.":[70],"find":[72],"that":[73,115],"constraint":[75],"encourages":[76],"capture":[79],"global,":[80],"semantic":[81],"features,":[82],"enables":[84,135],"direct":[85],"interpolation":[86],"between":[87],"images":[88,142,164],"without":[89],"a":[90,106,144],"learned":[91,132],"prior.":[92],"To":[93],"address":[94],"reduced":[96],"capacity":[98,119],"representations,":[101,176],"introduce":[103],"matching":[104,114],"quantization,":[105],"vector":[107],"algorithm":[109],"based":[110],"on":[111,151],"optimal":[112],"bipartite":[113],"increases":[116],"effective":[117],"bottleneck":[118],"by":[120],"$3.5\\times$":[121],"relative":[122],"naive":[124],"nearest-neighbour":[125],"quantization.":[126],"The":[127],"compositional":[128],"structure":[129],"further":[134],"interpolation-based":[136],"sampling,":[137],"allowing":[138],"synthesis":[139],"novel":[141],"single":[145],"forward":[146],"pass.":[147],"evaluate":[149],"PI-VQ":[150],"CelebA,":[152],"CelebA-HQ":[153],"FFHQ,":[155],"obtaining":[156],"competitive":[157],"precision,":[158],"density":[159],"coverage":[161],"metrics":[162],"synthesised":[165],"with":[166],"our":[167],"approach.":[168],"discuss":[170],"trade-offs":[172],"inherent":[173],"position-free":[175],"including":[177],"separability":[178],"interpretability":[180],"codes,":[184],"pointing":[185],"numerous":[187],"directions":[188],"future":[190],"work.":[191]},"counts_by_year":[],"updated_date":"2026-04-04T06:15:33.020886","created_date":"2026-04-04T00:00:00"}