A Novel Graph-based Framework for Explainable Image Classification: Features That Matter Article Swipe
Basim Azam
,
Brijesh Verma
,
Deepthi Praveenlal Kuttichira
,
Abdul Sattar
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1109/dicta60407.2023.00028
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1109/dicta60407.2023.00028
The efficacy of any machine learning model is largely contingent on the quality of the features used for training. Hence, the extraction of robust and discriminative features from raw data is a critical step. This task, however, presents significant challenges. Although modern deep learning models are very advanced, they are often criticized for their black-box nature. The predictions made by these models are not readily interpretable in terms of the features that influenced them. In our research, we propose a novel framework that innovatively combines the prowess of convolutional layers for feature extraction with robustness of Graph Neural Networks (GNNs) to model the relationships of neuron activations for better interpretability. The proposed architecture initially generates features to produce class-based neuron activations, these activations are then incorporated into graph structure. The GNN incorporates the relationship between neuron activations to produce final classifications. The proposed model provides explainability as in the predictions can be traced back to the specific neurons that contributed to them. The proposed model not only matches the accuracy of state-of-the-art models but also provides explainability through target class-specific feature importance.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/dicta60407.2023.00028
- OA Status
- green
- Cited By
- 1
- References
- 22
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4391305921
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4391305921Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/dicta60407.2023.00028Digital Object Identifier
- Title
-
A Novel Graph-based Framework for Explainable Image Classification: Features That MatterWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-11-28Full publication date if available
- Authors
-
Basim Azam, Brijesh Verma, Deepthi Praveenlal Kuttichira, Abdul SattarList of authors in order
- Landing page
-
https://doi.org/10.1109/dicta60407.2023.00028Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://hdl.handle.net/10072/429670Direct OA link when available
- Concepts
-
Interpretability, Computer science, Discriminative model, Artificial intelligence, Robustness (evolution), Feature extraction, Machine learning, Convolutional neural network, Graph, Pattern recognition (psychology), Black box, Theoretical computer science, Gene, Chemistry, BiochemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- References (count)
-
22Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4391305921 |
|---|---|
| doi | https://doi.org/10.1109/dicta60407.2023.00028 |
| ids.doi | https://doi.org/10.1109/dicta60407.2023.00028 |
| ids.openalex | https://openalex.org/W4391305921 |
| fwci | 0.25544289 |
| type | article |
| title | A Novel Graph-based Framework for Explainable Image Classification: Features That Matter |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 151 |
| biblio.first_page | 145 |
| topics[0].id | https://openalex.org/T12026 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994000196456909 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Explainable Artificial Intelligence (XAI) |
| topics[1].id | https://openalex.org/T11273 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9886000156402588 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Advanced Graph Neural Networks |
| topics[2].id | https://openalex.org/T10036 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.979200005531311 |
| 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 | Advanced Neural Network Applications |
| funders[0].id | https://openalex.org/F4320334704 |
| funders[0].ror | https://ror.org/05mmh0f86 |
| funders[0].display_name | Australian Research Council |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2781067378 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9511099457740784 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q17027399 |
| concepts[0].display_name | Interpretability |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7949219942092896 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C97931131 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7919524908065796 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q5282087 |
| concepts[2].display_name | Discriminative model |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.7283837199211121 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C63479239 |
| concepts[4].level | 3 |
| concepts[4].score | 0.7070407867431641 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[4].display_name | Robustness (evolution) |
| concepts[5].id | https://openalex.org/C52622490 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5864081382751465 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1026626 |
| concepts[5].display_name | Feature extraction |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.572388768196106 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C81363708 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5530239343643188 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[7].display_name | Convolutional neural network |
| concepts[8].id | https://openalex.org/C132525143 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4971971809864044 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[8].display_name | Graph |
| concepts[9].id | https://openalex.org/C153180895 |
| concepts[9].level | 2 |
| concepts[9].score | 0.49484795331954956 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[9].display_name | Pattern recognition (psychology) |
| concepts[10].id | https://openalex.org/C94966114 |
| concepts[10].level | 2 |
| concepts[10].score | 0.423518568277359 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q29256 |
| concepts[10].display_name | Black box |
| concepts[11].id | https://openalex.org/C80444323 |
| concepts[11].level | 1 |
| concepts[11].score | 0.10387250781059265 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[11].display_name | Theoretical computer science |
| concepts[12].id | https://openalex.org/C104317684 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[12].display_name | Gene |
| concepts[13].id | https://openalex.org/C185592680 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[13].display_name | Chemistry |
| concepts[14].id | https://openalex.org/C55493867 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[14].display_name | Biochemistry |
| keywords[0].id | https://openalex.org/keywords/interpretability |
| keywords[0].score | 0.9511099457740784 |
| keywords[0].display_name | Interpretability |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7949219942092896 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/discriminative-model |
| keywords[2].score | 0.7919524908065796 |
| keywords[2].display_name | Discriminative model |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.7283837199211121 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/robustness |
| keywords[4].score | 0.7070407867431641 |
| keywords[4].display_name | Robustness (evolution) |
| keywords[5].id | https://openalex.org/keywords/feature-extraction |
| keywords[5].score | 0.5864081382751465 |
| keywords[5].display_name | Feature extraction |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.572388768196106 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[7].score | 0.5530239343643188 |
| keywords[7].display_name | Convolutional neural network |
| keywords[8].id | https://openalex.org/keywords/graph |
| keywords[8].score | 0.4971971809864044 |
| keywords[8].display_name | Graph |
| keywords[9].id | https://openalex.org/keywords/pattern-recognition |
| keywords[9].score | 0.49484795331954956 |
| keywords[9].display_name | Pattern recognition (psychology) |
| keywords[10].id | https://openalex.org/keywords/black-box |
| keywords[10].score | 0.423518568277359 |
| keywords[10].display_name | Black box |
| keywords[11].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[11].score | 0.10387250781059265 |
| keywords[11].display_name | Theoretical computer science |
| language | en |
| locations[0].id | doi:10.1109/dicta60407.2023.00028 |
| locations[0].is_oa | False |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA) |
| locations[0].landing_page_url | https://doi.org/10.1109/dicta60407.2023.00028 |
| locations[1].id | pmh:oai:research-repository.griffith.edu.au:10072/429670 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306402548 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | Griffith Research Online (Griffith University, Queensland, Australia) |
| locations[1].source.host_organization | https://openalex.org/I11701301 |
| locations[1].source.host_organization_name | Griffith University |
| locations[1].source.host_organization_lineage | https://openalex.org/I11701301 |
| locations[1].license | other-oa |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | Conference output |
| locations[1].license_id | https://openalex.org/licenses/other-oa |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://hdl.handle.net/10072/429670 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5002895693 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3367-6467 |
| authorships[0].author.display_name | Basim Azam |
| authorships[0].countries | AU |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I11701301 |
| authorships[0].affiliations[0].raw_affiliation_string | IIIS, Griffith University, Brisbane, Australia |
| authorships[0].institutions[0].id | https://openalex.org/I11701301 |
| authorships[0].institutions[0].ror | https://ror.org/02sc3r913 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I11701301 |
| authorships[0].institutions[0].country_code | AU |
| authorships[0].institutions[0].display_name | Griffith University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Basim Azam |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | IIIS, Griffith University, Brisbane, Australia |
| authorships[1].author.id | https://openalex.org/A5026528338 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4618-0479 |
| authorships[1].author.display_name | Brijesh Verma |
| authorships[1].countries | AU |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I11701301 |
| authorships[1].affiliations[0].raw_affiliation_string | IIIS, Griffith University, Brisbane, Australia |
| authorships[1].institutions[0].id | https://openalex.org/I11701301 |
| authorships[1].institutions[0].ror | https://ror.org/02sc3r913 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I11701301 |
| authorships[1].institutions[0].country_code | AU |
| authorships[1].institutions[0].display_name | Griffith University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Brijesh Verma |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | IIIS, Griffith University, Brisbane, Australia |
| authorships[2].author.id | https://openalex.org/A5112736114 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Deepthi Praveenlal Kuttichira |
| authorships[2].countries | AU |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I11701301 |
| authorships[2].affiliations[0].raw_affiliation_string | IIIS, Griffith University, Brisbane, Australia |
| authorships[2].institutions[0].id | https://openalex.org/I11701301 |
| authorships[2].institutions[0].ror | https://ror.org/02sc3r913 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I11701301 |
| authorships[2].institutions[0].country_code | AU |
| authorships[2].institutions[0].display_name | Griffith University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Deepthi Praveenlal Kuttichira |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | IIIS, Griffith University, Brisbane, Australia |
| authorships[3].author.id | https://openalex.org/A5038675407 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-2567-2052 |
| authorships[3].author.display_name | Abdul Sattar |
| authorships[3].countries | AU |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I11701301 |
| authorships[3].affiliations[0].raw_affiliation_string | IIIS, Griffith University, Brisbane, Australia |
| authorships[3].institutions[0].id | https://openalex.org/I11701301 |
| authorships[3].institutions[0].ror | https://ror.org/02sc3r913 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I11701301 |
| authorships[3].institutions[0].country_code | AU |
| authorships[3].institutions[0].display_name | Griffith University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Abdul Sattar |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | IIIS, Griffith University, Brisbane, Australia |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | http://hdl.handle.net/10072/429670 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | A Novel Graph-based Framework for Explainable Image Classification: Features That Matter |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12026 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994000196456909 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Explainable Artificial Intelligence (XAI) |
| related_works | https://openalex.org/W2797441709, https://openalex.org/W2346578521, https://openalex.org/W4297660007, https://openalex.org/W2886918272, https://openalex.org/W4387589990, https://openalex.org/W2943982549, https://openalex.org/W3101055019, https://openalex.org/W2910028250, https://openalex.org/W4241566321, https://openalex.org/W3094353829 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:research-repository.griffith.edu.au:10072/429670 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306402548 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| 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 | Griffith Research Online (Griffith University, Queensland, Australia) |
| best_oa_location.source.host_organization | https://openalex.org/I11701301 |
| best_oa_location.source.host_organization_name | Griffith University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I11701301 |
| best_oa_location.license | other-oa |
| best_oa_location.pdf_url | |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | Conference output |
| best_oa_location.license_id | https://openalex.org/licenses/other-oa |
| 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://hdl.handle.net/10072/429670 |
| primary_location.id | doi:10.1109/dicta60407.2023.00028 |
| primary_location.is_oa | False |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA) |
| primary_location.landing_page_url | https://doi.org/10.1109/dicta60407.2023.00028 |
| publication_date | 2023-11-28 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W3182789783, https://openalex.org/W2898377853, https://openalex.org/W2657631929, https://openalex.org/W4286914341, https://openalex.org/W2919115771, https://openalex.org/W2962975498, https://openalex.org/W4306175885, https://openalex.org/W2962772482, https://openalex.org/W4318066384, https://openalex.org/W2891503716, https://openalex.org/W3021941048, https://openalex.org/W3124474911, https://openalex.org/W4297733535, https://openalex.org/W2778796877, https://openalex.org/W2963415211, https://openalex.org/W2907492528, https://openalex.org/W3152893301, https://openalex.org/W1849277567, https://openalex.org/W2151103935, https://openalex.org/W4295122555, https://openalex.org/W2161969291, https://openalex.org/W2921131065 |
| referenced_works_count | 22 |
| abstract_inverted_index.a | 31, 79 |
| abstract_inverted_index.In | 74 |
| abstract_inverted_index.as | 146 |
| abstract_inverted_index.be | 151 |
| abstract_inverted_index.by | 59 |
| abstract_inverted_index.in | 66, 147 |
| abstract_inverted_index.is | 7, 30 |
| abstract_inverted_index.of | 2, 13, 22, 68, 87, 95, 104, 170 |
| abstract_inverted_index.on | 10 |
| abstract_inverted_index.to | 100, 116, 137, 154, 160 |
| abstract_inverted_index.we | 77 |
| abstract_inverted_index.GNN | 130 |
| abstract_inverted_index.The | 0, 56, 110, 129, 141, 162 |
| abstract_inverted_index.and | 24 |
| abstract_inverted_index.any | 3 |
| abstract_inverted_index.are | 45, 49, 62, 123 |
| abstract_inverted_index.but | 173 |
| abstract_inverted_index.can | 150 |
| abstract_inverted_index.for | 17, 52, 90, 107 |
| abstract_inverted_index.not | 63, 165 |
| abstract_inverted_index.our | 75 |
| abstract_inverted_index.raw | 28 |
| abstract_inverted_index.the | 11, 14, 20, 69, 85, 102, 132, 148, 155, 168 |
| abstract_inverted_index.This | 34 |
| abstract_inverted_index.also | 174 |
| abstract_inverted_index.back | 153 |
| abstract_inverted_index.data | 29 |
| abstract_inverted_index.deep | 42 |
| abstract_inverted_index.from | 27 |
| abstract_inverted_index.into | 126 |
| abstract_inverted_index.made | 58 |
| abstract_inverted_index.only | 166 |
| abstract_inverted_index.that | 71, 82, 158 |
| abstract_inverted_index.then | 124 |
| abstract_inverted_index.they | 48 |
| abstract_inverted_index.used | 16 |
| abstract_inverted_index.very | 46 |
| abstract_inverted_index.with | 93 |
| abstract_inverted_index.Graph | 96 |
| abstract_inverted_index.final | 139 |
| abstract_inverted_index.graph | 127 |
| abstract_inverted_index.model | 6, 101, 143, 164 |
| abstract_inverted_index.novel | 80 |
| abstract_inverted_index.often | 50 |
| abstract_inverted_index.step. | 33 |
| abstract_inverted_index.task, | 35 |
| abstract_inverted_index.terms | 67 |
| abstract_inverted_index.their | 53 |
| abstract_inverted_index.them. | 73, 161 |
| abstract_inverted_index.these | 60, 121 |
| abstract_inverted_index.(GNNs) | 99 |
| abstract_inverted_index.Hence, | 19 |
| abstract_inverted_index.Neural | 97 |
| abstract_inverted_index.better | 108 |
| abstract_inverted_index.layers | 89 |
| abstract_inverted_index.models | 44, 61, 172 |
| abstract_inverted_index.modern | 41 |
| abstract_inverted_index.neuron | 105, 119, 135 |
| abstract_inverted_index.robust | 23 |
| abstract_inverted_index.target | 178 |
| abstract_inverted_index.traced | 152 |
| abstract_inverted_index.between | 134 |
| abstract_inverted_index.feature | 91, 180 |
| abstract_inverted_index.largely | 8 |
| abstract_inverted_index.machine | 4 |
| abstract_inverted_index.matches | 167 |
| abstract_inverted_index.nature. | 55 |
| abstract_inverted_index.neurons | 157 |
| abstract_inverted_index.produce | 117, 138 |
| abstract_inverted_index.propose | 78 |
| abstract_inverted_index.prowess | 86 |
| abstract_inverted_index.quality | 12 |
| abstract_inverted_index.readily | 64 |
| abstract_inverted_index.through | 177 |
| abstract_inverted_index.Although | 40 |
| abstract_inverted_index.Networks | 98 |
| abstract_inverted_index.accuracy | 169 |
| abstract_inverted_index.combines | 84 |
| abstract_inverted_index.critical | 32 |
| abstract_inverted_index.efficacy | 1 |
| abstract_inverted_index.features | 15, 26, 70, 115 |
| abstract_inverted_index.however, | 36 |
| abstract_inverted_index.learning | 5, 43 |
| abstract_inverted_index.presents | 37 |
| abstract_inverted_index.proposed | 111, 142, 163 |
| abstract_inverted_index.provides | 144, 175 |
| abstract_inverted_index.specific | 156 |
| abstract_inverted_index.advanced, | 47 |
| abstract_inverted_index.black-box | 54 |
| abstract_inverted_index.framework | 81 |
| abstract_inverted_index.generates | 114 |
| abstract_inverted_index.initially | 113 |
| abstract_inverted_index.research, | 76 |
| abstract_inverted_index.training. | 18 |
| abstract_inverted_index.contingent | 9 |
| abstract_inverted_index.criticized | 51 |
| abstract_inverted_index.extraction | 21, 92 |
| abstract_inverted_index.influenced | 72 |
| abstract_inverted_index.robustness | 94 |
| abstract_inverted_index.structure. | 128 |
| abstract_inverted_index.activations | 106, 122, 136 |
| abstract_inverted_index.challenges. | 39 |
| abstract_inverted_index.class-based | 118 |
| abstract_inverted_index.contributed | 159 |
| abstract_inverted_index.importance. | 181 |
| abstract_inverted_index.predictions | 57, 149 |
| abstract_inverted_index.significant | 38 |
| abstract_inverted_index.activations, | 120 |
| abstract_inverted_index.architecture | 112 |
| abstract_inverted_index.incorporated | 125 |
| abstract_inverted_index.incorporates | 131 |
| abstract_inverted_index.innovatively | 83 |
| abstract_inverted_index.relationship | 133 |
| abstract_inverted_index.convolutional | 88 |
| abstract_inverted_index.interpretable | 65 |
| abstract_inverted_index.relationships | 103 |
| abstract_inverted_index.class-specific | 179 |
| abstract_inverted_index.discriminative | 25 |
| abstract_inverted_index.explainability | 145, 176 |
| abstract_inverted_index.classifications. | 140 |
| abstract_inverted_index.state-of-the-art | 171 |
| abstract_inverted_index.interpretability. | 109 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.62365307 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |