Automated pest detection plays a critical role in supporting agricultural productivity by enabling accurate and efficient recognition of pest species in field conditions. This study presents a comparative evaluation and ablation analysis of four lightweight object detection models, namely YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n, for plant pest detection tasks. All models were trained and tested on the IP102 dataset, a large-scale benchmark comprising 102 pest categories captured across diverse field environments. Each model was evaluated under four optimization scenarios: AdamW optimizer, Mixup and Mosaic augmentation, a combination of both strategies, and Test-Time Augmentation (TTA). Performance was measured using precision, recall, F1-score, mAP@0.5, and mAP@0.5:0.95 to assess both detection accuracy and bounding box localization quality. The results demonstrate that YOLOv12n consistently achieves superior performance across the majority of evaluation metrics. Under the TTA scenario, YOLOv12n attained a precision of 0.590, recall of 0.698, F1-score of 0.639, mAP@0.5 of 0.689, and mAP@0.5:0.95 of 0.444, representing the highest scores among all evaluated configurations. TTA proved to be the most consistent optimization strategy, delivering stable improvements across all model architectures. In contrast, combining AdamW with data augmentation degraded performance across all models, likely due to over-regularization effects in lightweight network designs. These findings highlight that inference-level strategies can be more beneficial than training-level augmentation for compact detection models. This study provides practical insights for selecting and optimizing lightweight detectors in real-world agricultural deployment scenarios.
Joshua Pinem, Widi Astuti, A. Adiwijaya· International Conference on...· 0 citations
Lung disease remains a major global health concern, and accurate diagnosis using chest X-ray images plays a crucial role in supporting effective clinical decision-making. The contribution of this work lies in empirically demonstrating how internal redundancy removal through standard magnitude-based pruning can improve both performance and stability of an established CNN architecture. The COVID-Qu-Ex dataset was utilized, consisting of 11,956 COVID, 11,263 pneumonia, and 10,701 normal X-ray images. All models were trained under identical preprocessing, augmentation, and evaluation protocols, with three different random seeds to ensure result stability and reproducibility. Experimental results show that the pruned InceptionV3 model achieved superior performance, with an accuracy of 95.54% ± 0.0041, precision of 95.62% ± 0.0039, recall of 95.54% ± 0.0041, and F1-score of 95.54% ± 0.0041, outperforming the baseline InceptionV3 as well as other modern CNN architectures such as ResNet101 and VGG19. These findings demonstrate that network pruning can effectively reduce model redundancy while maintaining, and even improving, classification performance. Future work will focus on extending the proposed approach to other CNN architectures, integrating interpretability techniques, and addressing data imbalance issues to enhance clinical reliability.
Joshua Pinem, Widi Astuti, A. Adiwijaya· International Conference on...· 0 citations
Attention mechanisms are widely adopted in convolutional neural networks to improve feature representation, yet their consistent effectiveness in medical image classification remains uncertain. This study systematically evaluates channel and spatial attention mechanisms integrated into a ResNet50 architecture for chest X-ray classification tasks. Three attention configurations are examined, namely Squeeze-and-Excitation (SE), Convolutional Block Attention Module (CBAM), and a hybrid combination of both, using three publicly available chest X-ray datasets: Pneumonia Chest X-ray, COVID-QU-Ex, and Tuberculosis Chest X-ray. All model variants are trained under identical preprocessing and optimization settings to ensure a controlled and fair comparison. Each experiment is repeated across multiple random seeds to reduce the influence of stochastic variability, and final performance is reported as the mean across runs. Model effectiveness is assessed using accuracy, precision, recall, and F1 score, followed by paired t-tests to determine the statistical significance of observed differences. Quantitative results indicate that attention-augmented models produce marginal performance changes relative to the ResNet50 baseline across all three datasets. Statistical testing confirms that none of the observed improvements reach significance, with all p-values exceeding 0.05. These findings suggest that attention mechanisms do not function as universally effective performance boosters in chest X-ray classification. Instead, their role appears to be supportive in nature, contributing to feature representation stability rather than driving substantial predictive gains. Dataset characteristics and attention placement are identified as key factors influencing the degree of benefit observed.
