2020
DOI: 10.5114/ppn.2020.96975
|View full text |Cite
|
Sign up to set email alerts
|

Binary classification of pornographic and non-pornographic materials using the sAI 0.4 model and the modified sexACT database

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
1
0
1

Year Published

2022
2022
2022
2022

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 0 publications
0
1
0
1
Order By: Relevance
“…In order to select the best hyperparameters, a total of 26 studies were conducted, which were related to individual techniques of data augmentation, and an initial study related to the selection of the appropriate architecture of the neural network. To validate our study, we used four different datasets: CIFAR-10 [Kri00a], Intel Image Classification [Ban00a], sexACT 0.5 [Oro00a] and MNIST [LeC00a]. The first dataset consists of 60.000 color images categorized in 10 classes (e.g.…”
Section: Related Workmentioning
confidence: 99%
“…In order to select the best hyperparameters, a total of 26 studies were conducted, which were related to individual techniques of data augmentation, and an initial study related to the selection of the appropriate architecture of the neural network. To validate our study, we used four different datasets: CIFAR-10 [Kri00a], Intel Image Classification [Ban00a], sexACT 0.5 [Oro00a] and MNIST [LeC00a]. The first dataset consists of 60.000 color images categorized in 10 classes (e.g.…”
Section: Related Workmentioning
confidence: 99%
“…uzasadnienie w dalszej części artykułu), ponadto model cechował się niską dokładnością w wypadku klasyfikacji materiałów spoza zbioru treningowego. W związku z tym wytrenowano nowy model sieci neuronowej, oparty na modelu sAI 0.1 [10] oraz bazie sexACT [14]. Dalsze prowadzenie badań w tym kierunku przez rozwijanie obecnego modelu jest istotne z kilku powodów.…”
Section: Cel Oraz Uzasadnienie Badańunclassified