Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training Article Swipe
Xiaofeng Liu
,
Yuzhuo Han
,
Song Bai
,
Yi Ge
,
Tianxing Wang
,
Xu Han
,
Site Li
,
Jane You
,
Ju Lu
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2010.12440
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2010.12440
Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classifies each pixel into a pre-determined class. The widely-used cross entropy (CE) loss-based deep networks has achieved significant progress w.r.t. the mean Intersection-over Union (mIoU). However, the cross entropy loss can not take the different importance of each class in an self-driving system into account. For example, pedestrians in the image should be much more important than the surrounding buildings when make a decisions in the driving, so their segmentation results are expected to be as accurate as possible. In this paper, we propose to incorporate the importance-aware inter-class correlation in a Wasserstein training framework by configuring its ground distance matrix. The ground distance matrix can be pre-defined following a priori in a specific task, and the previous importance-ignored methods can be the particular cases. From an optimization perspective, we also extend our ground metric to a linear, convex or concave increasing function $w.r.t.$ pre-defined ground distance. We evaluate our method on CamVid and Cityscapes datasets with different backbones (SegNet, ENet, FCN and Deeplab) in a plug and play fashion. In our extenssive experiments, Wasserstein loss demonstrates superior segmentation performance on the predefined critical classes for safe-driving.
Related Topics
Concepts
Segmentation
Cross entropy
Artificial intelligence
Computer science
Pixel
Figure–ground
Entropy (arrow of time)
Pattern recognition (psychology)
Image segmentation
Class (philosophy)
Metric (unit)
Machine learning
Mathematical optimization
Mathematics
Perception
Biology
Neuroscience
Quantum mechanics
Operations management
Physics
Economics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2010.12440
- https://arxiv.org/pdf/2010.12440
- OA Status
- green
- Cited By
- 1
- References
- 35
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3093660441
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3093660441Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2010.12440Digital Object Identifier
- Title
-
Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein TrainingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-10-21Full publication date if available
- Authors
-
Xiaofeng Liu, Yuzhuo Han, Song Bai, Yi Ge, Tianxing Wang, Xu Han, Site Li, Jane You, Ju LuList of authors in order
- Landing page
-
https://arxiv.org/abs/2010.12440Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2010.12440Direct 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/2010.12440Direct OA link when available
- Concepts
-
Segmentation, Cross entropy, Artificial intelligence, Computer science, Pixel, Figure–ground, Entropy (arrow of time), Pattern recognition (psychology), Image segmentation, Class (philosophy), Metric (unit), Machine learning, Mathematical optimization, Mathematics, Perception, Biology, Neuroscience, Quantum mechanics, Operations management, Physics, EconomicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2020: 1Per-year citation counts (last 5 years)
- References (count)
-
35Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3093660441 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2010.12440 |
| ids.doi | https://doi.org/10.48550/arxiv.2010.12440 |
| ids.mag | 3093660441 |
| ids.openalex | https://openalex.org/W3093660441 |
| fwci | |
| type | preprint |
| title | Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Neural Network Applications |
| topics[1].id | https://openalex.org/T11099 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9991999864578247 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2203 |
| topics[1].subfield.display_name | Automotive Engineering |
| topics[1].display_name | Autonomous Vehicle Technology and Safety |
| topics[2].id | https://openalex.org/T10331 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9976000189781189 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Video Surveillance and Tracking Methods |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C89600930 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7032868266105652 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[0].display_name | Segmentation |
| concepts[1].id | https://openalex.org/C167981619 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6687514185905457 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1685498 |
| concepts[1].display_name | Cross entropy |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6033680438995361 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5897961854934692 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C160633673 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4725867211818695 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q355198 |
| concepts[4].display_name | Pixel |
| concepts[5].id | https://openalex.org/C104319648 |
| concepts[5].level | 3 |
| concepts[5].score | 0.45721909403800964 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1412040 |
| concepts[5].display_name | Figure–ground |
| concepts[6].id | https://openalex.org/C106301342 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4536430835723877 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q4117933 |
| concepts[6].display_name | Entropy (arrow of time) |
| concepts[7].id | https://openalex.org/C153180895 |
| concepts[7].level | 2 |
| concepts[7].score | 0.42884647846221924 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[7].display_name | Pattern recognition (psychology) |
| concepts[8].id | https://openalex.org/C124504099 |
| concepts[8].level | 3 |
| concepts[8].score | 0.4221300482749939 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q56933 |
| concepts[8].display_name | Image segmentation |
| concepts[9].id | https://openalex.org/C2777212361 |
| concepts[9].level | 2 |
| concepts[9].score | 0.42183348536491394 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[9].display_name | Class (philosophy) |
| concepts[10].id | https://openalex.org/C176217482 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4149476885795593 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q860554 |
| concepts[10].display_name | Metric (unit) |
| concepts[11].id | https://openalex.org/C119857082 |
| concepts[11].level | 1 |
| concepts[11].score | 0.36492717266082764 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[11].display_name | Machine learning |
| concepts[12].id | https://openalex.org/C126255220 |
| concepts[12].level | 1 |
| concepts[12].score | 0.3256321847438812 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[12].display_name | Mathematical optimization |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.3244684338569641 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C26760741 |
| concepts[14].level | 2 |
| concepts[14].score | 0.25327494740486145 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q160402 |
| concepts[14].display_name | Perception |
| concepts[15].id | https://openalex.org/C86803240 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[15].display_name | Biology |
| concepts[16].id | https://openalex.org/C169760540 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[16].display_name | Neuroscience |
| concepts[17].id | https://openalex.org/C62520636 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[17].display_name | Quantum mechanics |
| concepts[18].id | https://openalex.org/C21547014 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q1423657 |
| concepts[18].display_name | Operations management |
| concepts[19].id | https://openalex.org/C121332964 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[19].display_name | Physics |
| concepts[20].id | https://openalex.org/C162324750 |
| concepts[20].level | 0 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[20].display_name | Economics |
| keywords[0].id | https://openalex.org/keywords/segmentation |
| keywords[0].score | 0.7032868266105652 |
| keywords[0].display_name | Segmentation |
| keywords[1].id | https://openalex.org/keywords/cross-entropy |
| keywords[1].score | 0.6687514185905457 |
| keywords[1].display_name | Cross entropy |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6033680438995361 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5897961854934692 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/pixel |
| keywords[4].score | 0.4725867211818695 |
| keywords[4].display_name | Pixel |
| keywords[5].id | https://openalex.org/keywords/figure–ground |
| keywords[5].score | 0.45721909403800964 |
| keywords[5].display_name | Figure–ground |
| keywords[6].id | https://openalex.org/keywords/entropy |
| keywords[6].score | 0.4536430835723877 |
| keywords[6].display_name | Entropy (arrow of time) |
| keywords[7].id | https://openalex.org/keywords/pattern-recognition |
| keywords[7].score | 0.42884647846221924 |
| keywords[7].display_name | Pattern recognition (psychology) |
| keywords[8].id | https://openalex.org/keywords/image-segmentation |
| keywords[8].score | 0.4221300482749939 |
| keywords[8].display_name | Image segmentation |
| keywords[9].id | https://openalex.org/keywords/class |
| keywords[9].score | 0.42183348536491394 |
| keywords[9].display_name | Class (philosophy) |
| keywords[10].id | https://openalex.org/keywords/metric |
| keywords[10].score | 0.4149476885795593 |
| keywords[10].display_name | Metric (unit) |
| keywords[11].id | https://openalex.org/keywords/machine-learning |
| keywords[11].score | 0.36492717266082764 |
| keywords[11].display_name | Machine learning |
| keywords[12].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[12].score | 0.3256321847438812 |
| keywords[12].display_name | Mathematical optimization |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.3244684338569641 |
| keywords[13].display_name | Mathematics |
| keywords[14].id | https://openalex.org/keywords/perception |
| keywords[14].score | 0.25327494740486145 |
| keywords[14].display_name | Perception |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2010.12440 |
| 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/2010.12440 |
| 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/2010.12440 |
| locations[1].id | doi:10.48550/arxiv.2010.12440 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2010.12440 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100359288 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4514-2016 |
| authorships[0].author.display_name | Xiaofeng Liu |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I2801851002 |
| authorships[0].affiliations[0].raw_affiliation_string | Harvard University , |
| authorships[0].institutions[0].id | https://openalex.org/I2801851002 |
| authorships[0].institutions[0].ror | https://ror.org/006v7bf86 |
| authorships[0].institutions[0].type | other |
| authorships[0].institutions[0].lineage | https://openalex.org/I136199984, https://openalex.org/I2801851002 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Harvard University Press |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xiaofeng Liu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Harvard University , |
| authorships[1].author.id | https://openalex.org/A5079221047 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Yuzhuo Han |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I27357992 |
| authorships[1].affiliations[0].raw_affiliation_string | Dalian University of Technology |
| authorships[1].institutions[0].id | https://openalex.org/I27357992 |
| authorships[1].institutions[0].ror | https://ror.org/023hj5876 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I27357992 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Dalian University of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yuzhuo Han |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Dalian University of Technology |
| authorships[2].author.id | https://openalex.org/A5101562162 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2570-9118 |
| authorships[2].author.display_name | Song Bai |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I134446601, https://openalex.org/I95457486 |
| authorships[2].affiliations[0].raw_affiliation_string | UC Berkeley#TAB# |
| authorships[2].institutions[0].id | https://openalex.org/I134446601 |
| authorships[2].institutions[0].ror | https://ror.org/02xewxa75 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I134446601 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Berkeley College |
| authorships[2].institutions[1].id | https://openalex.org/I95457486 |
| authorships[2].institutions[1].ror | https://ror.org/01an7q238 |
| authorships[2].institutions[1].type | education |
| authorships[2].institutions[1].lineage | https://openalex.org/I95457486 |
| authorships[2].institutions[1].country_code | US |
| authorships[2].institutions[1].display_name | University of California, Berkeley |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Song Bai |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | UC Berkeley#TAB# |
| authorships[3].author.id | https://openalex.org/A5042059973 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7186-9024 |
| authorships[3].author.display_name | Yi Ge |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I74973139 |
| authorships[3].affiliations[0].raw_affiliation_string | Carnegie Mellon University |
| authorships[3].institutions[0].id | https://openalex.org/I74973139 |
| authorships[3].institutions[0].ror | https://ror.org/05x2bcf33 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I74973139 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Carnegie Mellon University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yi Ge |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Carnegie Mellon University |
| authorships[4].author.id | https://openalex.org/A5076885869 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Tianxing Wang |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I24943067 |
| authorships[4].affiliations[0].raw_affiliation_string | FUDAN UNIVERSITY |
| authorships[4].institutions[0].id | https://openalex.org/I24943067 |
| authorships[4].institutions[0].ror | https://ror.org/013q1eq08 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I24943067 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Fudan University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Tianxing Wang |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | FUDAN UNIVERSITY |
| authorships[5].author.id | https://openalex.org/A5102012659 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-3491-8576 |
| authorships[5].author.display_name | Xu Han |
| authorships[5].countries | US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I145311948 |
| authorships[5].affiliations[0].raw_affiliation_string | Johns Hopkins University |
| authorships[5].institutions[0].id | https://openalex.org/I145311948 |
| authorships[5].institutions[0].ror | https://ror.org/00za53h95 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I145311948 |
| authorships[5].institutions[0].country_code | US |
| authorships[5].institutions[0].display_name | Johns Hopkins University |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Xu Han |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Johns Hopkins University |
| authorships[6].author.id | https://openalex.org/A5000578374 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-7221-1814 |
| authorships[6].author.display_name | Site Li |
| authorships[6].countries | US |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I74973139 |
| authorships[6].affiliations[0].raw_affiliation_string | Carnegie Mellon University |
| authorships[6].institutions[0].id | https://openalex.org/I74973139 |
| authorships[6].institutions[0].ror | https://ror.org/05x2bcf33 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I74973139 |
| authorships[6].institutions[0].country_code | US |
| authorships[6].institutions[0].display_name | Carnegie Mellon University |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Site Li |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Carnegie Mellon University |
| authorships[7].author.id | https://openalex.org/A5045562050 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-8181-4836 |
| authorships[7].author.display_name | Jane You |
| authorships[7].countries | HK |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I14243506 |
| authorships[7].affiliations[0].raw_affiliation_string | The Hong Kong Polytechnic University. |
| authorships[7].institutions[0].id | https://openalex.org/I14243506 |
| authorships[7].institutions[0].ror | https://ror.org/0030zas98 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I14243506 |
| authorships[7].institutions[0].country_code | HK |
| authorships[7].institutions[0].display_name | Hong Kong Polytechnic University |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Jane You |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | The Hong Kong Polytechnic University. |
| authorships[8].author.id | https://openalex.org/A5079472589 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-7010-3799 |
| authorships[8].author.display_name | Ju Lu |
| authorships[8].countries | US |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I2801851002 |
| authorships[8].affiliations[0].raw_affiliation_string | Harvard University , |
| authorships[8].institutions[0].id | https://openalex.org/I2801851002 |
| authorships[8].institutions[0].ror | https://ror.org/006v7bf86 |
| authorships[8].institutions[0].type | other |
| authorships[8].institutions[0].lineage | https://openalex.org/I136199984, https://openalex.org/I2801851002 |
| authorships[8].institutions[0].country_code | US |
| authorships[8].institutions[0].display_name | Harvard University Press |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Ju Lu |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | Harvard University , |
| 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/2010.12440 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2020-10-29T00:00:00 |
| display_name | Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Neural Network Applications |
| related_works | https://openalex.org/W2048788251, https://openalex.org/W2044641672, https://openalex.org/W2174043808, https://openalex.org/W2047929095, https://openalex.org/W2898826419, https://openalex.org/W2153888769, https://openalex.org/W4253526137, https://openalex.org/W2128279936, https://openalex.org/W2377040216, https://openalex.org/W2994927414 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2020 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2010.12440 |
| 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/2010.12440 |
| 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/2010.12440 |
| primary_location.id | pmh:oai:arXiv.org:2010.12440 |
| 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/2010.12440 |
| 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/2010.12440 |
| publication_date | 2020-10-21 |
| publication_year | 2020 |
| referenced_works | https://openalex.org/W2963881378, https://openalex.org/W2541678333, https://openalex.org/W2948801556, https://openalex.org/W2606492274, https://openalex.org/W2987686867, https://openalex.org/W2340897893, https://openalex.org/W2913282330, https://openalex.org/W2412782625, https://openalex.org/W2158131535, https://openalex.org/W3002155012, https://openalex.org/W2741701287, https://openalex.org/W2793613699, https://openalex.org/W2143668817, https://openalex.org/W2911933223, https://openalex.org/W1903029394, https://openalex.org/W174895128, https://openalex.org/W2793132020, https://openalex.org/W2951798229, https://openalex.org/W2989128580, https://openalex.org/W2966760706, https://openalex.org/W2964184973, https://openalex.org/W2997018136, https://openalex.org/W2102368172, https://openalex.org/W2993534970, https://openalex.org/W2985406498, https://openalex.org/W2085491337, https://openalex.org/W2964334477, https://openalex.org/W2419448466, https://openalex.org/W2898795295, https://openalex.org/W1996777517, https://openalex.org/W2794638914, https://openalex.org/W3048761984, https://openalex.org/W2601315196, https://openalex.org/W2790592899, https://openalex.org/W2903204734 |
| referenced_works_count | 35 |
| abstract_inverted_index.a | 18, 76, 105, 123, 126, 150, 179 |
| abstract_inverted_index.In | 93, 184 |
| abstract_inverted_index.We | 161 |
| abstract_inverted_index.an | 4, 54, 140 |
| abstract_inverted_index.as | 89, 91 |
| abstract_inverted_index.be | 66, 88, 120, 135 |
| abstract_inverted_index.by | 109 |
| abstract_inverted_index.in | 53, 62, 78, 104, 125, 178 |
| abstract_inverted_index.is | 3 |
| abstract_inverted_index.of | 50 |
| abstract_inverted_index.on | 165, 194 |
| abstract_inverted_index.or | 153 |
| abstract_inverted_index.so | 81 |
| abstract_inverted_index.to | 87, 98, 149 |
| abstract_inverted_index.we | 96, 143 |
| abstract_inverted_index.FCN | 175 |
| abstract_inverted_index.For | 59 |
| abstract_inverted_index.The | 21, 115 |
| abstract_inverted_index.and | 11, 129, 167, 176, 181 |
| abstract_inverted_index.are | 85 |
| abstract_inverted_index.can | 44, 119, 134 |
| abstract_inverted_index.for | 8, 199 |
| abstract_inverted_index.has | 29 |
| abstract_inverted_index.its | 111 |
| abstract_inverted_index.not | 45 |
| abstract_inverted_index.our | 146, 163, 185 |
| abstract_inverted_index.the | 34, 40, 47, 63, 71, 79, 100, 130, 136, 195 |
| abstract_inverted_index.(CE) | 25 |
| abstract_inverted_index.(SS) | 2 |
| abstract_inverted_index.From | 139 |
| abstract_inverted_index.also | 144 |
| abstract_inverted_index.cars | 10 |
| abstract_inverted_index.deep | 27 |
| abstract_inverted_index.each | 15, 51 |
| abstract_inverted_index.into | 17, 57 |
| abstract_inverted_index.loss | 43, 189 |
| abstract_inverted_index.make | 75 |
| abstract_inverted_index.mean | 35 |
| abstract_inverted_index.more | 68 |
| abstract_inverted_index.much | 67 |
| abstract_inverted_index.play | 182 |
| abstract_inverted_index.plug | 180 |
| abstract_inverted_index.take | 46 |
| abstract_inverted_index.than | 70 |
| abstract_inverted_index.this | 94 |
| abstract_inverted_index.when | 74 |
| abstract_inverted_index.with | 170 |
| abstract_inverted_index.ENet, | 174 |
| abstract_inverted_index.Union | 37 |
| abstract_inverted_index.class | 52 |
| abstract_inverted_index.cross | 23, 41 |
| abstract_inverted_index.image | 64 |
| abstract_inverted_index.pixel | 16 |
| abstract_inverted_index.task, | 128 |
| abstract_inverted_index.their | 82 |
| abstract_inverted_index.which | 13 |
| abstract_inverted_index.CamVid | 166 |
| abstract_inverted_index.cases. | 138 |
| abstract_inverted_index.class. | 20 |
| abstract_inverted_index.convex | 152 |
| abstract_inverted_index.extend | 145 |
| abstract_inverted_index.ground | 112, 116, 147, 159 |
| abstract_inverted_index.manner | 7 |
| abstract_inverted_index.matrix | 118 |
| abstract_inverted_index.method | 164 |
| abstract_inverted_index.metric | 148 |
| abstract_inverted_index.paper, | 95 |
| abstract_inverted_index.priori | 124 |
| abstract_inverted_index.should | 65 |
| abstract_inverted_index.system | 56 |
| abstract_inverted_index.w.r.t. | 33 |
| abstract_inverted_index.(mIoU). | 38 |
| abstract_inverted_index.classes | 198 |
| abstract_inverted_index.concave | 154 |
| abstract_inverted_index.entropy | 24, 42 |
| abstract_inverted_index.linear, | 151 |
| abstract_inverted_index.matrix. | 114 |
| abstract_inverted_index.methods | 133 |
| abstract_inverted_index.propose | 97 |
| abstract_inverted_index.results | 84 |
| abstract_inverted_index.$w.r.t.$ | 157 |
| abstract_inverted_index.(SegNet, | 173 |
| abstract_inverted_index.Deeplab) | 177 |
| abstract_inverted_index.However, | 39 |
| abstract_inverted_index.Semantic | 0 |
| abstract_inverted_index.account. | 58 |
| abstract_inverted_index.accurate | 90 |
| abstract_inverted_index.achieved | 30 |
| abstract_inverted_index.critical | 197 |
| abstract_inverted_index.datasets | 169 |
| abstract_inverted_index.distance | 113, 117 |
| abstract_inverted_index.driving, | 80 |
| abstract_inverted_index.evaluate | 162 |
| abstract_inverted_index.example, | 60 |
| abstract_inverted_index.expected | 86 |
| abstract_inverted_index.fashion. | 183 |
| abstract_inverted_index.function | 156 |
| abstract_inverted_index.networks | 28 |
| abstract_inverted_index.previous | 131 |
| abstract_inverted_index.progress | 32 |
| abstract_inverted_index.specific | 127 |
| abstract_inverted_index.superior | 191 |
| abstract_inverted_index.training | 107 |
| abstract_inverted_index.backbones | 172 |
| abstract_inverted_index.buildings | 73 |
| abstract_inverted_index.decisions | 77 |
| abstract_inverted_index.different | 48, 171 |
| abstract_inverted_index.distance. | 160 |
| abstract_inverted_index.following | 122 |
| abstract_inverted_index.framework | 108 |
| abstract_inverted_index.important | 5, 69 |
| abstract_inverted_index.possible. | 92 |
| abstract_inverted_index.robotics, | 12 |
| abstract_inverted_index.Cityscapes | 168 |
| abstract_inverted_index.classifies | 14 |
| abstract_inverted_index.extenssive | 186 |
| abstract_inverted_index.importance | 49 |
| abstract_inverted_index.increasing | 155 |
| abstract_inverted_index.loss-based | 26 |
| abstract_inverted_index.particular | 137 |
| abstract_inverted_index.perception | 6 |
| abstract_inverted_index.predefined | 196 |
| abstract_inverted_index.Wasserstein | 106, 188 |
| abstract_inverted_index.configuring | 110 |
| abstract_inverted_index.correlation | 103 |
| abstract_inverted_index.incorporate | 99 |
| abstract_inverted_index.inter-class | 102 |
| abstract_inverted_index.pedestrians | 61 |
| abstract_inverted_index.performance | 193 |
| abstract_inverted_index.pre-defined | 121, 158 |
| abstract_inverted_index.significant | 31 |
| abstract_inverted_index.surrounding | 72 |
| abstract_inverted_index.widely-used | 22 |
| abstract_inverted_index.demonstrates | 190 |
| abstract_inverted_index.experiments, | 187 |
| abstract_inverted_index.optimization | 141 |
| abstract_inverted_index.perspective, | 142 |
| abstract_inverted_index.segmentation | 1, 83, 192 |
| abstract_inverted_index.self-driving | 9, 55 |
| abstract_inverted_index.safe-driving. | 200 |
| abstract_inverted_index.pre-determined | 19 |
| abstract_inverted_index.importance-aware | 101 |
| abstract_inverted_index.Intersection-over | 36 |
| abstract_inverted_index.importance-ignored | 132 |
| cited_by_percentile_year | |
| countries_distinct_count | 3 |
| institutions_distinct_count | 9 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/11 |
| sustainable_development_goals[0].score | 0.8600000143051147 |
| sustainable_development_goals[0].display_name | Sustainable cities and communities |
| citation_normalized_percentile |