• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1282-1289
• /
• 2017

Since the study of deep convolutional neural network became prevalent, one of the important discoveries is that a feature map from a convolutional network can be extracted before going into the fully connected layer and can be used as a saliency map for object detection. Furthermore, the model can use features from each different layer for accurate object detection: the features from different layers can have different properties. As the model goes deeper, it has many latent skip connections and feature maps to elaborate object detection. Although there are many intermediate layers that we can use for semantic segmentation through skip connection, still the characteristics of each skip connection and the best skip connection for this task are uncertain. Therefore, in this study, we exhaustively research skip connections of state-of-the-art deep convolutional networks and investigate the characteristics of the features from each intermediate layer. In addition, this study would suggest how to use a recent deep neural network model for semantic segmentation and it would therefore become a cornerstone for later studies with the state-of-the-art network models.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.322-327
• /
• 2017

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long-Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment's result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.633-642
• /
• 2019

Recently, the convolution neural network (CNN) model at a single image super-resolution (SISR) have been very successful. The residual learning method can improve training stability and network performance in CNN. In this paper, we propose a SISR using recursive residual network architecture by introducing dense skip connections for learning nonlinear mapping from low-resolution input image to high-resolution target image. The proposed SISR method adopts a method of the recursive residual learning to mitigate the difficulty of the deep network training and remove unnecessary modules for easier to optimize in CNN layers because of the concise and compact recursive network via dense skip connection method. The proposed method not only alleviates the vanishing-gradient problem of a very deep network, but also get the outstanding performance with low complexity of neural network, which allows the neural network to perform training, thereby exhibiting improved performance of SISR method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.444-447
• /
• 2022

In recent years, computer vision image classification tasks have become faster and better due to deeper neural network architectures. But while most image classification tasks are designed to classify images based on specific image features (such as distinguishing between cats and dogs), there are not many classification models that have been trained to distinguish between time periods such as day and night or different seasons of the year. And while some research has been done into distinguishing between seasons in images of the same location, this paper presents a varied approach to the problem of seasonal classification of generic images. Three methods for seasonal image classification, from simple feature extraction, to building a convolutional neural network, to transfer learning were studied and the accuracy results were compared and analyzed.