Transactions on Machine Learning and Artificial Intelligence

Masking the Backgrounds to Produce Object-Focused Images and Comparing that Augmentation Method to Other Methods

2022-04-17T02:31:21+00:00

Image augmentation is a very powerful method to expand existing image datasets. This paper presents a novel method for creating a variation of existing images, called Object-Focused Image (OFI). This is when an image includes only the labeled object and everything else is made white. This paper elaborates on the OFI approach, explores its efficiency, and compares the validation accuracy of 780 notebooks. The presented testbed makes use of a subset of ImageNet Dataset (8,000 images of 14 classes) and incorporates all available models in Keras. These 26 models are tested before augmentation and after applying 9 different categories of augmentation methods. Each of these 260 notebooks is tested in 3 different scenarios: scenario A (ImageNet weights are not used and network layers are trainable), scenario B (ImageNet weights are used and network layers are trainable) and scenario C (ImageNet weights are used and network layers are not trainable). The experiments presented in this paper show that using OFI images along with the original images can be better than other augmentation methods in 16.4% of the cases. It was also shown that OFI method could help some models learn although they could not learn when other augmentation methods were applied. The conducted experiments also proved that the Kernel filters and the color space transformations are among the best data augmentation methods.

Recognition of Geometric Images by Linguistic Method

2022-04-15T11:01:20+00:00

Image recognition is currently one of the fastest-growing areas in applied mathematics. Of the many methods for solving problems in this area, the grammatical (linguistic) method of pattern recognition is the least studied. The essence of the grammar method is to construct appropriate grammar for object classes. In this case, the object recognition problem is related to the language generated by the given grammar. Using the linguistic method, an algorithm and software for recognizing geometric images have been developed. While the development the following tasks were solved. Methods have been developed for describing geometric images (triangles, squares, polygons) and corresponding grammars have been constructed for them so that the chains generated by this grammar represent objects of this class. The problems of constructing given classes of geometric images, as well as constructing a grammar for each class, are solved.

At the training stage, classes are considered, each of which is described by a finite set of chains. To classify a new image, that is, to determine which class it belongs to, a parsing of the corresponding chain of this image was performed using grammars. Thus, the belonging of the chain to the language born by this grammar was clarified.

Ensemble Graph Attention Networks

2022-05-18T00:20:31+00:00

Graph neural networks have demonstrated its success in many applications on graph-structured data. Many efforts have been devoted to elaborating new network architectures and learning algorithms over the past decade. The exploration of applying ensemble learning techniques to enhance existing graph algorithms have been overlooked. In this work, we propose a simple generic bagging-based ensemble learning strategy which is applicable to any backbone graph models. We then propose two ensemble graph neural network models – Ensemble-GAT and Ensemble-HetGAT by applying the ensemble strategy to the graph attention network (GAT), and a heterogeneous graph attention network (HetGAT). We demonstrate the effectiveness of the proposed ensemble strategy on GAT and HetGAT through comprehensive experiments with four real-world homogeneous graph datasets and three real-world heterogeneous graph datasets on node classification tasks. The proposed Ensemble-GAT and Ensemble-HetGAT outperform the state-of-the-art graph neural network and heterogeneous graph neural network models on most of the benchmark datasets. The proposed ensemble strategy also alleviates the over-smoothing problem in GAT and HetGAT.