A study of self-training variants for semi-supervised image classification
2021 doctoral thesis by Attaullah Sahito at University of Waikato
Press Enter · cited answer in seconds
0 sources
Summary
A study of self-training variants for semi-supervised image classification is a doctoral thesis[1].
Key Facts
- A study of self-training variants for semi-supervised image classification authored Attaullah Sahito[2].
- A study of self-training variants for semi-supervised image classification's instance of is recorded as doctoral thesis[3].
- A study of self-training variants for semi-supervised image classification was published by Waikato Research Commons[4].
- A study of self-training variants for semi-supervised image classification's place of publication is recorded as Hamilton[5].
- A study of self-training variants for semi-supervised image classification's language of work or name is recorded as English[6].
- A study of self-training variants for semi-supervised image classification's country of origin is recorded as New Zealand[7].
- A study of self-training variants for semi-supervised image classification was published on 2021[8].
- A study of self-training variants for semi-supervised image classification's main subject is computer vision[9].
- A study of self-training variants for semi-supervised image classification's main subject is artificial intelligence[10].
- A study of self-training variants for semi-supervised image classification's main subject is transfer learning[11].
- A study of self-training variants for semi-supervised image classification's main subject is artificial neural network[12].
- A study of self-training variants for semi-supervised image classification's main subject is image processing[13].
- A study of self-training variants for semi-supervised image classification's main subject is machine learning[14].
- A study of self-training variants for semi-supervised image classification's main subject is self-supervised learning[15].
- A study of self-training variants for semi-supervised image classification's main subject is semi-supervised learning[16].
- A study of self-training variants for semi-supervised image classification's work available at URL is recorded as https://researchcommons.waikato.ac.nz/handle/10289/14678[17].
- A study of self-training variants for semi-supervised image classification's title is recorded as A study of self-training variants for semi-supervised image classification[18].
- A study of self-training variants for semi-supervised image classification's copyright holder is recorded as Attaullah Sahito[19].
- A study of self-training variants for semi-supervised image classification's thesis submitted to is recorded as University of Waikato[20].
- A study of self-training variants for semi-supervised image classification's on focus list of Wikimedia project is recorded as NZThesisProject[21].
- A study of self-training variants for semi-supervised image classification's copyright status is recorded as copyrighted[22].
- A study of self-training variants for semi-supervised image classification's online access status is recorded as open access[23].
- A study of self-training variants for semi-supervised image classification's thesis committee member is recorded as Bernhard Pfahringer[24].
- A study of self-training variants for semi-supervised image classification's thesis committee member is recorded as Eibe Frank[25].
- A study of self-training variants for semi-supervised image classification's thesis submitted for degree is recorded as Doctor of Philosophy[26].
Body
Designation and Status
A study of self-training variants for semi-supervised image classification's instance of is recorded as doctoral thesis[3].