Shared Visual Representations of Drawing for Communication: How do\n different biases affect human interpretability and intent? Article Swipe
Daniela Mihai
,
Jonathon Hare
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.08203
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.08203
We present an investigation into how representational losses can affect the\ndrawings produced by artificial agents playing a communication game. Building\nupon recent advances, we show that a combination of powerful pretrained encoder\nnetworks, with appropriate inductive biases, can lead to agents that draw\nrecognisable sketches, whilst still communicating well. Further, we start to\ndevelop an approach to help automatically analyse the semantic content being\nconveyed by a sketch and demonstrate that current approaches to inducing\nperceptual biases lead to a notion of objectness being a key feature despite\nthe agent training being self-supervised.\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2110.08203
- https://arxiv.org/pdf/2110.08203
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4285035752
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4285035752Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2110.08203Digital Object Identifier
- Title
-
Shared Visual Representations of Drawing for Communication: How do\n different biases affect human interpretability and intent?Work title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-10-15Full publication date if available
- Authors
-
Daniela Mihai, Jonathon HareList of authors in order
- Landing page
-
https://arxiv.org/abs/2110.08203Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2110.08203Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2110.08203Direct OA link when available
- Concepts
-
Interpretability, Sketch, Computer science, Affect (linguistics), Key (lock), Feature (linguistics), Artificial intelligence, Human–computer interaction, Perception, Psychology, Communication, Linguistics, Neuroscience, Algorithm, Computer security, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4285035752 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2110.08203 |
| ids.openalex | https://openalex.org/W4285035752 |
| fwci | 0.0 |
| type | preprint |
| title | Shared Visual Representations of Drawing for Communication: How do\n different biases affect human interpretability and intent? |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12650 |
| topics[0].field.id | https://openalex.org/fields/28 |
| topics[0].field.display_name | Neuroscience |
| topics[0].score | 0.942300021648407 |
| topics[0].domain.id | https://openalex.org/domains/1 |
| topics[0].domain.display_name | Life Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2805 |
| topics[0].subfield.display_name | Cognitive Neuroscience |
| topics[0].display_name | Aesthetic Perception and Analysis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2781067378 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8775752782821655 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q17027399 |
| concepts[0].display_name | Interpretability |
| concepts[1].id | https://openalex.org/C2779231336 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7056079506874084 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7534724 |
| concepts[1].display_name | Sketch |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6963256597518921 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C2776035688 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6644694805145264 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1606558 |
| concepts[3].display_name | Affect (linguistics) |
| concepts[4].id | https://openalex.org/C26517878 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5160953402519226 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q228039 |
| concepts[4].display_name | Key (lock) |
| concepts[5].id | https://openalex.org/C2776401178 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5012836456298828 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[5].display_name | Feature (linguistics) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.4944803714752197 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C107457646 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4788551330566406 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[7].display_name | Human–computer interaction |
| concepts[8].id | https://openalex.org/C26760741 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4698086380958557 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q160402 |
| concepts[8].display_name | Perception |
| concepts[9].id | https://openalex.org/C15744967 |
| concepts[9].level | 0 |
| concepts[9].score | 0.19570201635360718 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[9].display_name | Psychology |
| concepts[10].id | https://openalex.org/C46312422 |
| concepts[10].level | 1 |
| concepts[10].score | 0.18167996406555176 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11024 |
| concepts[10].display_name | Communication |
| concepts[11].id | https://openalex.org/C41895202 |
| concepts[11].level | 1 |
| concepts[11].score | 0.07834181189537048 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[11].display_name | Linguistics |
| concepts[12].id | https://openalex.org/C169760540 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[12].display_name | Neuroscience |
| concepts[13].id | https://openalex.org/C11413529 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[13].display_name | Algorithm |
| concepts[14].id | https://openalex.org/C38652104 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[14].display_name | Computer security |
| concepts[15].id | https://openalex.org/C138885662 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[15].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/interpretability |
| keywords[0].score | 0.8775752782821655 |
| keywords[0].display_name | Interpretability |
| keywords[1].id | https://openalex.org/keywords/sketch |
| keywords[1].score | 0.7056079506874084 |
| keywords[1].display_name | Sketch |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6963256597518921 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/affect |
| keywords[3].score | 0.6644694805145264 |
| keywords[3].display_name | Affect (linguistics) |
| keywords[4].id | https://openalex.org/keywords/key |
| keywords[4].score | 0.5160953402519226 |
| keywords[4].display_name | Key (lock) |
| keywords[5].id | https://openalex.org/keywords/feature |
| keywords[5].score | 0.5012836456298828 |
| keywords[5].display_name | Feature (linguistics) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.4944803714752197 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[7].score | 0.4788551330566406 |
| keywords[7].display_name | Human–computer interaction |
| keywords[8].id | https://openalex.org/keywords/perception |
| keywords[8].score | 0.4698086380958557 |
| keywords[8].display_name | Perception |
| keywords[9].id | https://openalex.org/keywords/psychology |
| keywords[9].score | 0.19570201635360718 |
| keywords[9].display_name | Psychology |
| keywords[10].id | https://openalex.org/keywords/communication |
| keywords[10].score | 0.18167996406555176 |
| keywords[10].display_name | Communication |
| keywords[11].id | https://openalex.org/keywords/linguistics |
| keywords[11].score | 0.07834181189537048 |
| keywords[11].display_name | Linguistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2110.08203 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2110.08203 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2110.08203 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5102783686 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3368-9062 |
| authorships[0].author.display_name | Daniela Mihai |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mihai, Daniela |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5067505586 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2921-4283 |
| authorships[1].author.display_name | Jonathon Hare |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Hare, Jonathon |
| authorships[1].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2110.08203 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-12T00:00:00 |
| display_name | Shared Visual Representations of Drawing for Communication: How do\n different biases affect human interpretability and intent? |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12650 |
| primary_topic.field.id | https://openalex.org/fields/28 |
| primary_topic.field.display_name | Neuroscience |
| primary_topic.score | 0.942300021648407 |
| primary_topic.domain.id | https://openalex.org/domains/1 |
| primary_topic.domain.display_name | Life Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2805 |
| primary_topic.subfield.display_name | Cognitive Neuroscience |
| primary_topic.display_name | Aesthetic Perception and Analysis |
| related_works | https://openalex.org/W2905433371, https://openalex.org/W4390569940, https://openalex.org/W2888392564, https://openalex.org/W4310278675, https://openalex.org/W4388422664, https://openalex.org/W2806259446, https://openalex.org/W4361193272, https://openalex.org/W2963326959, https://openalex.org/W2378994405, https://openalex.org/W4312407344 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2110.08203 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2110.08203 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2110.08203 |
| primary_location.id | pmh:oai:arXiv.org:2110.08203 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2110.08203 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2110.08203 |
| publication_date | 2021-10-15 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 16, 25, 61, 73, 78 |
| abstract_inverted_index.We | 0 |
| abstract_inverted_index.an | 2, 50 |
| abstract_inverted_index.by | 12, 60 |
| abstract_inverted_index.of | 27, 75 |
| abstract_inverted_index.to | 37, 52, 68, 72 |
| abstract_inverted_index.we | 22, 47 |
| abstract_inverted_index.and | 63 |
| abstract_inverted_index.can | 8, 35 |
| abstract_inverted_index.how | 5 |
| abstract_inverted_index.key | 79 |
| abstract_inverted_index.the | 56 |
| abstract_inverted_index.help | 53 |
| abstract_inverted_index.into | 4 |
| abstract_inverted_index.lead | 36, 71 |
| abstract_inverted_index.show | 23 |
| abstract_inverted_index.that | 24, 39, 65 |
| abstract_inverted_index.with | 31 |
| abstract_inverted_index.agent | 82 |
| abstract_inverted_index.being | 77, 84 |
| abstract_inverted_index.game. | 18 |
| abstract_inverted_index.start | 48 |
| abstract_inverted_index.still | 43 |
| abstract_inverted_index.well. | 45 |
| abstract_inverted_index.affect | 9 |
| abstract_inverted_index.agents | 14, 38 |
| abstract_inverted_index.biases | 70 |
| abstract_inverted_index.losses | 7 |
| abstract_inverted_index.notion | 74 |
| abstract_inverted_index.recent | 20 |
| abstract_inverted_index.sketch | 62 |
| abstract_inverted_index.whilst | 42 |
| abstract_inverted_index.analyse | 55 |
| abstract_inverted_index.biases, | 34 |
| abstract_inverted_index.content | 58 |
| abstract_inverted_index.current | 66 |
| abstract_inverted_index.feature | 80 |
| abstract_inverted_index.playing | 15 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.Further, | 46 |
| abstract_inverted_index.approach | 51 |
| abstract_inverted_index.powerful | 28 |
| abstract_inverted_index.produced | 11 |
| abstract_inverted_index.semantic | 57 |
| abstract_inverted_index.training | 83 |
| abstract_inverted_index.advances, | 21 |
| abstract_inverted_index.inductive | 33 |
| abstract_inverted_index.sketches, | 41 |
| abstract_inverted_index.approaches | 67 |
| abstract_inverted_index.artificial | 13 |
| abstract_inverted_index.objectness | 76 |
| abstract_inverted_index.pretrained | 29 |
| abstract_inverted_index.appropriate | 32 |
| abstract_inverted_index.combination | 26 |
| abstract_inverted_index.demonstrate | 64 |
| abstract_inverted_index.to\ndevelop | 49 |
| abstract_inverted_index.despite\nthe | 81 |
| abstract_inverted_index.automatically | 54 |
| abstract_inverted_index.communicating | 44 |
| abstract_inverted_index.communication | 17 |
| abstract_inverted_index.investigation | 3 |
| abstract_inverted_index.the\ndrawings | 10 |
| abstract_inverted_index.Building\nupon | 19 |
| abstract_inverted_index.being\nconveyed | 59 |
| abstract_inverted_index.representational | 6 |
| abstract_inverted_index.draw\nrecognisable | 40 |
| abstract_inverted_index.encoder\nnetworks, | 30 |
| abstract_inverted_index.self-supervised.\n | 85 |
| abstract_inverted_index.inducing\nperceptual | 69 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile.value | 0.22093563 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |