Search

Capsule networks exhibit the potential to enhance computer vision tasks through their utilization of equivariance for capturing spatial relationships. However, the broader adoption of these networks has been impeded by the computational complexity of their routing mechanism and shallow backbone model. To address these challenges, this paper introduces an innovative hybrid architecture that seamlessly integrates a pretrained backbone model with a task-specific capsule head (CapsHead). Our methodology is extensively evaluated across a range of classification and segmentation tasks, encompassing diverse datasets. The empirical findings robustly underscore the efficacy and practical feasibility of our proposed approach in real-world vision applications. Notably, our approach yields substantial 3.45% and 6.24% enhancement in linear evaluation on the CIFAR10 dataset and segmentation on the VOC2012 dataset, respectively, compared to baselines that do not incorporate the capsule head. This research offers a noteworthy contribution by not only advancing the application of capsule networks, but also mitigating their computational complexities. The results substantiate the feasibility of our hybrid architecture, thereby paving the way for a wider integration of capsule networks into various computer vision tasks.

Forecasting, commonly used in econometrics, meteorology, or energy consumption prediction, is the field of study that deals with time series data to predict future trends. Former studies have revealed that both traditional statistical models and recent deep learning-based approaches have achieved good performance in forecasting. In particular, temporal convolutional networks (TCNs) have proved their effectiveness in several time series benchmarks. However, presented TCN models are too heavy to deploy on resource-constrained systems, such as edge devices. As a resolution, this study proposes a stride–dilation mechanism for TCN that favors a lightweight model yet still achieves on-pair accuracy with the heavy counterparts. We also present the Chonnam National University (CNU) Electric Power Consumption dataset, the dataset of energy consumption measured at CNU by smart meters every hour. The experimental results indicate that our best model reduces the mean squared error by 32.7%, whereas the model size is only 1.6% compared to the baseline TCN.

In the face of increasing irregular temperature patterns and climate shifts, the need for accurate power consumption prediction is becoming increasingly important to ensure a steady supply of electricity. Existing deep learning models have sought to improve prediction accuracy but commonly require greater computational demands. In this research, on the other hand, we introduce DelayNet, a lightweight deep learning model that maintains model efficiency while accommodating extended time sequences. Our DelayNet is designed based on the observation that electronic series data exhibit recurring irregular patterns over time. Furthermore, we present two substantial datasets of electricity consumption records from South Korean buildings spanning nearly two years. Empirical findings demonstrate the model’s performance, achieving 21.23%, 43.60%, 17.05% and 21.71% improvement compared to recurrent neural networks, gated-recurrent units, temporal convolutional neural networks and ARIMA models, as well as greatly reducing model complexity and computational requirements. These findings indicate the potential for micro-level power consumption planning, as lightweight models can be implemented on edge devices.

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.

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.