2019 IEEE International Conference on Software Maintenance and Evolution (ICSME) 2019
DOI: 10.1109/icsme.2019.00051
|View full text |Cite
|
Sign up to set email alerts
|

Losing Confidence in Quality: Unspoken Evolution of Computer Vision Services

Abstract: Recent advances in artificial intelligence (AI) and machine learning (ML), such as computer vision, are now available as intelligent services and their accessibility and simplicity is compelling. Multiple vendors now offer this technology as cloud services and developers want to leverage these advances to provide value to end-users. However, there is no firm investigation into the maintenance and evolution risks arising from use of these intelligent services; in particular, their behavioural consistency and tr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
29
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
3
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 22 publications
(29 citation statements)
references
References 30 publications
0
29
0
Order By: Relevance
“…According to Cummaudo et al [19] and Hosseini et al [20], the development of intelligent services differs from the usual web services, as they are developed with components based on artificial intelligence (AI).…”
Section: Intelligent Servicesmentioning
confidence: 99%
“…According to Cummaudo et al [19] and Hosseini et al [20], the development of intelligent services differs from the usual web services, as they are developed with components based on artificial intelligence (AI).…”
Section: Intelligent Servicesmentioning
confidence: 99%
“…According to Cummaudo et al [14] and Hosseini et al [15], the development of intelligent services differs from the usual web services, as they are developed with components based on artificial intelligence (AI).…”
Section: Intelligent Servicesmentioning
confidence: 99%
“…The predictions performed by the intelligent services focus only on training data sets and the results obtained are presented as probabilities that the inference satisfies one or more labels in the training data [14].…”
Section: Intelligent Servicesmentioning
confidence: 99%
See 1 more Smart Citation
“…However, unlike traditional web services, the functionality of these intelligent services is dependent on a set of assumptions unique to ML [6]. These assumptions are based on the data used to train ML algorithms, the choice of algorithm, and the choice of data processing stepsÐmost of which are not documented.…”
mentioning
confidence: 99%