2019
DOI: 10.1007/978-3-030-33676-9_29
|View full text |Cite
|
Sign up to set email alerts
|

Not Just a Matter of Semantics: The Relationship Between Visual and Semantic Similarity

Abstract: Knowledge transfer, zero-shot learning and semantic image retrieval are methods that aim at improving accuracy by utilizing semantic information, e.g., from WordNet. It is assumed that this information can augment or replace missing visual data in the form of labeled training images because semantic similarity correlates with visual similarity. This assumption may seem trivial, but is crucial for the application of such semantic methods. Any violation can cause mispredictions. Thus, it is important to examine … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
1
1

Relationship

2
4

Authors

Journals

citations
Cited by 10 publications
(1 citation statement)
references
References 33 publications
(35 reference statements)
0
1
0
Order By: Relevance
“…The slightly worse accuracy without any noise is possibly due to problematic assumptions about the correlation between visual and semantic similarity [30], [2]. This affects CHILLAX negatively, because it is based on hierarchical classification.…”
Section: B Imprecision Onlymentioning
confidence: 99%
“…The slightly worse accuracy without any noise is possibly due to problematic assumptions about the correlation between visual and semantic similarity [30], [2]. This affects CHILLAX negatively, because it is based on hierarchical classification.…”
Section: B Imprecision Onlymentioning
confidence: 99%