Attention Guided Relation Network for Few-Shot Image Classification
Autor: | Khan Mohammad Habibullah, Arani Shawkat Mauree, Imranul Ashrafi, Muntasir Mohammad |
---|---|
Rok vydání: | 2019 |
Předmět: |
Contextual image classification
Computer science business.industry 02 engineering and technology 010501 environmental sciences Complex network Machine learning computer.software_genre 01 natural sciences Residual neural network Categorization 0202 electrical engineering electronic engineering information engineering Embedding 020201 artificial intelligence & image processing Artificial intelligence business computer Classifier (UML) 0105 earth and related environmental sciences |
Zdroj: | Proceedings of the 2019 7th International Conference on Computer and Communications Management. |
Popis: | Few-shot Learning is an object categorization problem where the classifier attempts to distinguish new classes with very few labeled examples. There has been significant progress in this field, which includes complex network architectures. Most of the works done in this field were focused on small datasets and longer training. In this paper, the experimentation was done with limited episodic training architecture, which consists of Relation Network as classification network, ResNet Embedding as embedding module, and Self Attention as attention mechanism. The experimentation and comparison with the state-of-the-art models show that attention with metric-based meta-learning generalizes quicker in short training and yields good results. The architecture was tested on the complex dataset miniImageNet. The accuracy was found to be 62.9%, which is close to the state-of-the-art architecture described on metric based meta-learning. |
Databáze: | OpenAIRE |
Externí odkaz: |