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.

Vision–language models (VLMs) have achieved remarkable success in natural image domains, yet their potential remains underexplored in agriculture due to the lack of high-quality, joint image–text datasets. To address this limitation, we introduce VL-PAW (Vision–Language dataset for Pear, Apple, and Weed), a dataset comprising 3.9 K image–caption pairs for two key agricultural tasks: weed species classification and fruit inspection. We fine-tune the CLIP model on VL-PAW and gain several insights. First, the model demonstrates impressive zero-shot performance, achieving 98.21% accuracy in classifying coarse labels. Second, for fine-grained categories, the vision–language model outperforms vision-only models in both few-shot settings and entire dataset training (1-shot: 56.79%; 2-shot: 72.82%; 3-shot: 74.49%; 10-shot: 83.85%). Third, using intuitive captions enhances fine-grained fruit inspection performance compared to using class names alone. These findings demonstrate the applicability of VLMs in future agricultural querying systems.

Data augmentation (DA) is a universal technique to reduce overfitting and improve the robustness of machine learning models by increasing the quantity and variety of the training dataset. Although data augmentation is essential in vision tasks, it is rarely applied to text datasets since it is less straightforward. Some studies have concerned text data augmentation, but most of them are for the majority languages, such as English or French. There have been only a few studies on data augmentation for minority languages, e.g., Korean. This study fills the gap by demonstrating several common data augmentation methods and Korean corpora with pre-trained language models. In short, we evaluate the performance of two text data augmentation approaches, known as text transformation and back translation. We compare these augmentations among Korean corpora on four downstream tasks: semantic textual similarity (STS), natural language inference (NLI), question duplication verification (QDV), and sentiment classification (STC). Compared to cases without augmentation, the performance gains when applying text data augmentation are 2.24%, 2.19%, 0.66%, and 0.08% on the STS, NLI, QDV, and STC tasks, respectively.

Accurate inspection of subtle defects on apple surfaces is necessary in agricultural engineering. However, existing methods often rely on expensive equipment and encounter difficulty in detecting small defect areas effectively. To address this challenge, we introduce the Subtle Surface Defects in Apples (SSDA) dataset, a custom dataset specifically collected and annotated for two defect types: scratches and pest damage. For benchmarking, we propose a heatmap-based anchor-free (HAFREE) detector, a novel end-to-end object detection architecture designed to localize subtle defects on apple surfaces. Unlike prior methods that rely on anchor boxes, HAFREE employs a heatmap-based approach to represent defects as keypoints using two-dimensional Gaussian heatmaps. We introduce a multiscale feature fusion block, targeting small objects by incorporating local and global contextual information. To mitigate overfitting, we also implement a patch training strategy incorporating full images and cropped patches during training as a regularizer. The proposed method achieves a mAP50 of 50.05% on the SSDA dataset, outperforming one- and two-stage anchor-based detectors and previous anchor-free approaches. Code is available at: https://github.com/nbngochan/HAFREE.

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.

This study explores the integration of concept bottleneck models (CBMs) with knowledge distillation (KD) while preserving the locality characteristics of the CBM. Although KD proves effective in model compression, compressed models often lack interpretability in their decision-making process. We enhance comprehensive explainability by maintaining CBMs’ inherent interpretability through our novel approach to knowledge distillation. We introduce visual concept knowledge distillation (VICO-KD), which transfers both explicit and implicit visual concepts from the teacher to the student model while preserving the local interpretability of the CBM, enabling accurate classification and clear visualization of evidence. VICO-KD demonstrates superior performance on benchmark datasets compared to Vanilla-KD, ensuring the student model learns visual concepts while maintaining the local interpretation capabilities of the teacher CBM. Our methodology shows competitive performance against existing concept models, and the student model, trained via VICO-KD, exhibits enhanced performance compared to the teacher during interventions. This study highlights the effectiveness of combining a CBM with KD to improve both interpretability and explainability in compressed models while maintaining locality properties.