Application of embeddings for multi-class classification with optional extendability
Вантажиться...
Дата
2024
Автори
Науковий керівник
Назва журналу
Номер ISSN
Назва тому
Видавець
КПІ ім. Ігоря Сікорського
Анотація
This study investigates the feasibility of an expandable image classification method, utilizing a convolutional neural network to generate embeddings for use with simpler machine learning algorithms. The possibility of utilizing this approach to add new classes by additional training without modifying the topology of the vectorization network was shown on two datasets: MNIST and Fashion-MNIST. The findings indicate that this approach can reduce retraining time and complexity, particularly for more complex image classification tasks, and also offers additional capabilities such as similarity search in vector databases. However, for simpler tasks, conventional classification networks remain more time-efficient.
Опис
Ключові слова
multiclass classification, convolutional neural networks, embeddings, embedding-based classification, image classification
Бібліографічний опис
Smilianets, F. Application of embeddings for multi-class classification with optional extendability / F. Smilianets // Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2024. – № 2 (45). – С. 186-193. – Бібліогр.: 8 назв.