Search

This study introduces "shortcut routing," a novel routing mechanism in capsule networks that addresses computational inefficiencies by directly activating global capsules from local capsules, eliminating intermediate layers. An attention-based approach with fuzzy coefficients is also explored for improved efficiency. Experimental results on Mnist, smallnorb, and affNist datasets show comparable classification performance, achieving accuracies of 99.52%, 93.91%, and 89.02% respectively. The proposed fuzzy-based and attention-based routing methods significantly reduce the number of calculations by 1.42 and 2.5 times compared to EM routing, highlighting their computational advantages in capsule networks. These findings contribute to the advancement of efficient and accurate hierarchical pattern representation models., 8 pages, published at IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences E104.A(8)

This work discusses the challenges of multi-label image classification and presents a novel Efficient Shuffle Net (EffShuffNet) based on a convolutional neural network (CNN) architecture to address these challenges. Multi-label classification is difficult as the complexity of prediction increases with the number of labels and classes, and current multi-model approaches require optimized deep learning models which increase computational costs. The EffShuff block divides the input feature map into two parts and processes them differently, with one half undergoing a lightweight convolution and the other half undergoing average pooling. The EffShuff transition component shuffles the feature maps after lightweight convolution, resulting in a 57.9% reduction in computational cost compared to ShuffleNetv2. Furthermore, we propose EffShuff-Dense architecture, which incorporates Dense connection to further emphasize low-level features. In experiments, the EffShuffNet achieved 96.975% accuracy in age and gender classification, which is 5.83% higher than the state-of-the-art, while EffShuffDenseNet was even better with 97.63% accuracy. Additionally, the proposed models were found to have better classification performance with smaller model sizes in fine-grained image classification experiments.

Utilizing pre-trained models involves fully or partially using pre-trained parameters as initialization. In general, configuring a pre-trained model demands practitioners’ knowledge about problems or an exhaustive trial–error experiment according to a given task. In this paper, we propose tuning trainable layers using a genetic algorithm on a pre-trained model that is fine-tuned on single-channel image datasets for a classification task. The single-channel dataset comprises images from grayscale and preprocessed audio signals transformed into a log-Mel spectrogram. Four deep-learning models used in the experimental evaluation employed the pre-trained model with the ImageNet dataset. The proposed genetic algorithm was applied to find the highest fitness for every generation to determine the selective layer tuning of the pre-trained models. Compared to the conventional fine-tuning method and random layer search, our proposed selective layer search with a genetic algorithm achieves higher accuracy, on average, by 9.7% and 1.88% (MNIST-Fashion), 1.31% and 1.14% (UrbanSound8k), and 2.2% and 0.29% (HospitalAlarmSound), respectively. In addition, our searching method can naturally be applied to various datasets of the same task without prior knowledge about the dataset of interest.

Graph convolutional neural networks (GCNNs) have been successfully applied to a wide range of problems, including low-dimensional Euclidean structural domains representing images, videos, and speech and high-dimensional non-Euclidean domains, such as social networks and chemical molecular structures. However, in computer vision, the existing GCNNs are not provided with positional information to distinguish between graphs of new structures; therefore, the performance of the image classification domain represented by arbitrary graphs is significantly poor. In this work, we introduce how to initialize the positional information through a random walk algorithm and continuously learn the additional position-embedded information of various graph structures represented over the superpixel images we choose for efficiency. We call this method the graph convolutional network with learnable positional embedding applied on images (IMGCN-LPE). We apply IMGCN-LPE to three graph convolutional models (the Chebyshev graph convolutional network, graph convolutional network, and graph attention network) to validate performance on various benchmark image datasets. As a result, although not as impressive as convolutional neural networks, the proposed method outperforms various other conventional convolutional methods and demonstrates its effectiveness among the same tasks in the field of GCNNs.

Recent empirical works reveal that visual representation learned by deep neural networks can be successfully used as descriptors for image retrieval. A common technique is to leverage pre-trained models to learn visual descriptors by ranking losses and fine-tuning with labeled data. However, retrieval systems’ performance significantly decreases when querying images of lower resolution than the training images. This study considered a contrastive learning framework fine-tuned on features extracted from a pre-trained neural network encoder equipped with an attention mechanism to address the image retrieval task for low-resolution image retrieval. Our method is simple yet effective since the contrastive learning framework drives similar samples close to each other in feature space by manipulating variants of their augmentations. To benchmark the proposed framework, we conducted quantitative and qualitative analyses of CARS196 (mAP = 0.8804), CUB200-2011 (mAP = 0.9379), and Stanford Online Products datasets (mAP = 0.9141) and analyzed their performances.

Researchers and entertainment companies have given lots of attention to virtual reality over the past decade. 3D multi-view is a technology that provides interactions that are similar to those in the real world. However, 3D video streaming has a high data transfer rate because we must transmit multimedia data at a rate several times higher than that used for regular streaming. Besides, network throughput is unstable due to the inherent limitations of network infrastructure, which degrades video streaming quality. Additionally, network failure can occur frequently, causing stalling in multimedia playback. Hence, a network system is required to have more than one backup route in order to successfully guarantee the reliability of a network at all times. Furthermore, in the field of multi-view transmission, not much research has been published that has been conducted in a network virtualization environment. Therefore, we present a study on adaptive-based, high-efficiency video coding with three-dimensional, multi-view streaming over a peer-to-peer network. First, we study adaptive bitrate streaming methods based on high-efficiency video coding. Then we research transmitting multi-view data over a multi-path system. In the experiment, we first record a video from different views using five cameras. Next we merge recorded videos from the five cameras into a file and encode it before transmitting it over the peer-to-peer network. Moreover, we build a virtualized system using Docker virtualization technology and network function virtualization. The results of the experiment show that transmitting high-volume data over a multi-path network channel increases the streaming buffer level, which is about 20% higher than an adaptive streaming 3D method. It also makes the video quality 4% higher than in an HEVC-based adaptive streaming method.