
Ð’ данной работе были раÑÑмотрены оÑновные оÑобенноÑти, ÑвÑзанные Ñ Ñ€Ð°Ð±Ð¾Ñ‚Ð¾Ð¹ над неÑбаланÑированными данными, и оÑновные проблемы при клаÑÑификации изображений. Разобраны принципы работы модификаций генеративно-ÑоÑÑ‚Ñзательных Ñетей и произведён Ñравнительный анализ Ñ Ð¸Ñпользованием неÑкольких метрик их работы над небаланÑированными клаÑÑами изображений.
In this paper, the main features associated with working on unbalanced data and the main problems in image classification were considered. The principles of operation of modifications of generative-adversarial networks are analyzed and a comparative analysis is made using several metrics of their work on unbalanced classes of images.
авÑоÑнкодеÑ, autoencoder, class imbalance, generative adversarial network, неÑбаланÑиÑованноÑÑÑ ÐºÐ»Ð°ÑÑов, генеÑаÑивно-ÑоÑÑÑзаÑелÑÐ½Ð°Ñ ÑеÑÑ
авÑоÑнкодеÑ, autoencoder, class imbalance, generative adversarial network, неÑбаланÑиÑованноÑÑÑ ÐºÐ»Ð°ÑÑов, генеÑаÑивно-ÑоÑÑÑзаÑелÑÐ½Ð°Ñ ÑеÑÑ
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
