arXiv subjects

Thi-Thu-Hong Phan

Publications and source records attributed to Thi-Thu-Hong Phan.

7 recordsLinked to original sources

arXiv2026

Cross-Architectural Mixture-of-Experts with Adaptive Soft Routing for Plant Leaf Disease Classification

Plant leaf disease classification is crucial for crop protection and precision agriculture but remains challenging under complex backgrounds, illumination variations, and severe class imbalance. Moreover, single-architecture models often fail to effectively capture both local and global representations. To address these challenges, this study proposes an adaptive soft Mixture-of-Experts (MoE) framework with cross-architectural routing that integrates EfficientNet-B0, DenseNet-121, and Swin-Tiny to exploit complementary multi-scale, local, and global features. A soft gating mechanism dynamically assigns input-dependent expert weights, while a two-stage refinement training strategy improves optimization stability and generalization. Experiments on a highly imbalanced potato leaf disease dataset achieve 91.68% recall and 92.62% F1-score, surpassing the strongest individual expert by 5.91% and 5.03%, respectively. Additional evaluations on durian and sesame leaf disease datasets yield F1-scores of 94.03% and 97.04%, demonstrating robust cross-dataset generalization and the potential of the proposed framework for reliable real-world crop health monitoring

cs.AI↗

arXiv2026

AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification

Automated leaf disease classification is critical for early disease detection in resource-constrained field environments. Vision Transformers (ViTs) provide strong representation capability by modeling long-range dependencies and inter-class relationships; however, their high computational cost makes them impractical for deployment on edge devices. As a result, existing approaches struggle to effectively transfer these rich representations to lightweight models. This paper introduces AgriKD, a cross-architecture knowledge distillation framework for efficient edge deployment, which transfers knowledge from a Vision Transformer (ViT) teacher to a compact convolutional student model. To bridge the representational gap between Transformer and CNN architectures, the proposed approach integrates multiple distillation objectives at the output, feature, and relational levels, where each objective captures a different aspect of the teacher knowledge. This enables the student model to better preserve and utilize transformer-derived global representations. Experiments on multiple leaf disease datasets show that the distilled student achieves performance comparable to the teacher while significantly improving efficiency, reducing model parameters by approximately 172 times, computational cost by 47.57 times, and inference latency by 18-22 times. Furthermore, the optimized model is deployed across multiple runtime formats, including ONNX, TFLite Float16, and TensorRT FP16, achieving consistent predictive performance with negligible accuracy degradation. Real-world deployment on NVIDIA Jetson edge devices and a mobile application demonstrates reliable real-time inference, highlighting the practicality of AgriKD for AI-powered agricultural applications in resource-constrained environments.

cs.CV↗

arXiv2026

Enhanced Fish Freshness Classification with Incremental Handcrafted Feature Fusion

Accurate assessment of fish freshness remains a major challenge in the food industry, with direct consequences for product quality, market value, and consumer health. Conventional sensory evaluation is inherently subjective, inconsistent, and difficult to standardize across contexts, often limited by subtle, species-dependent spoilage cues. To address these limitations, we propose a handcrafted feature-based approach that systematically extracts and incrementally fuses complementary descriptors, including color statistics, histograms across multiple color spaces, and texture features such as Local Binary Patterns (LBP) and Gray-Level Co-occurrence Matrices (GLCM), from fish eye images. Our method captures global chromatic variations from full images and localized degradations from ROI segments, fusing each independently to evaluate their effectiveness in assessing freshness. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate the approach's effectiveness: in a standard train-test setting, a LightGBM classifier achieved 77.56% accuracy, a 14.35% improvement over the previous deep learning baseline of 63.21%. With augmented data, an Artificial Neural Network (ANN) reached 97.49% accuracy, surpassing the prior best of 77.3% by 20.19%. These results demonstrate that carefully engineered, handcrafted features, when strategically processed, yield a robust, interpretable, and reliable solution for automated fish freshness assessment, providing valuable insights for practical applications in food quality monitoring.

cs.AI↗

arXiv2025

Multi-objective hybrid knowledge distillation for efficient deep learning in smart agriculture

Deploying deep learning models on resource-constrained edge devices remains a major challenge in smart agriculture due to the trade-off between computational efficiency and recognition accuracy. To address this challenge, this study proposes a hybrid knowledge distillation framework for developing a lightweight yet high-performance convolutional neural network. The proposed approach designs a customized student model that combines inverted residual blocks with dense connectivity and trains it under the guidance of a ResNet18 teacher network using a multi-objective strategy that integrates hard-label supervision, feature-level distillation, response-level distillation, and self-distillation. Experiments are conducted on a rice seed variety identification dataset containing nine varieties and further extended to four plant leaf disease datasets, including rice, potato, coffee, and corn, to evaluate generalization capability. On the rice seed variety classification task, the distilled student model achieves an accuracy of 98.56%, which is only 0.09% lower than the teacher model (98.65%), while requiring only 0.68 GFLOPs and approximately 1.07 million parameters. This corresponds to a reduction of about 2.7 times in computational cost and more than 10 times in model size compared with the ResNet18 teacher model. In addition, compared with representative pretrained models, the proposed student reduces the number of parameters by more than 6 times relative to DenseNet121 and by over 80 times compared with the Vision Transformer (ViT) architecture, while maintaining comparable or superior classification accuracy. Consistent performance gains across multiple plant leaf disease datasets further demonstrate the robustness, efficiency, and strong deployment potential of the proposed framework for hardware-limited smart agriculture systems.

cs.CV↗

arXiv2025

Deep Feature Optimization for Enhanced Fish Freshness Assessment

Assessing fish freshness is vital for ensuring food safety and minimizing economic losses in the seafood industry. However, traditional sensory evaluation remains subjective, time-consuming, and inconsistent. Although recent advances in deep learning have automated visual freshness prediction, challenges related to accuracy and feature transparency persist. This study introduces a unified three-stage framework that refines and leverages deep visual representations for reliable fish freshness assessment. First, five state-of-the-art vision architectures - ResNet-50, DenseNet-121, EfficientNet-B0, ConvNeXt-Base, and Swin-Tiny - are fine-tuned to establish a strong baseline. Next, multi-level deep features extracted from these backbones are used to train seven classical machine learning classifiers, integrating deep and traditional decision mechanisms. Finally, feature selection methods based on Light Gradient Boosting Machine (LGBM), Random Forest, and Lasso identify a compact and informative subset of features. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate that the best configuration combining Swin-Tiny features, an Extra Trees classifier, and LGBM-based feature selection achieves an accuracy of 85.99%, outperforming recent studies on the same dataset by 8.69-22.78%. These findings confirm the effectiveness and generalizability of the proposed framework for visual quality evaluation tasks.

cs.CV↗

arXiv2025

Towards Accurate and Efficient Waste Image Classification: A Hybrid Deep Learning and Machine Learning Approach

Automated image-based garbage classification is a critical component of global waste management; however, systematic benchmarks that integrate Machine Learning (ML), Deep Learning (DL), and efficient hybrid solutions remain underdeveloped. This study provides a comprehensive comparison of three paradigms: (1) machine learning algorithms using handcrafted features, (2) deep learning architectures, including ResNet variants and EfficientNetV2S, and (3) a hybrid approach that utilizes deep models for feature extraction combined with classical classifiers such as Support Vector Machine and Logistic Regression to identify the most effective strategy. Experiments on three public datasets - TrashNet, Garbage Classification, and a refined Household Garbage Dataset (with 43 corrected mislabels)- demonstrate that the hybrid method consistently outperforms the others, achieving up to 100% accuracy on TrashNet and the refined Household set, and 99.87% on Garbage Classification, thereby surpassing state-of-the-art benchmarks. Furthermore, feature selection reduces feature dimensionality by over 95% without compromising accuracy, resulting in faster training and inference. This work establishes more reliable benchmarks for waste classification and introduces an efficient hybrid framework that achieves high accuracy while reducing inference cost, making it suitable for scalable deployment in resource-constrained environments.

cs.CV↗

arXiv2017

Comparative study on supervised learning methods for identifying phytoplankton species

Phytoplankton plays an important role in marine ecosystem. It is defined as a biological factor to assess marine quality. The identification of phytoplankton species has a high potential for monitoring environmental, climate changes and for evaluating water quality. However, phytoplankton species identification is not an easy task owing to their variability and ambiguity due to thousands of micro and pico-plankton species. Therefore, the aim of this paper is to build a framework for identifying phytoplankton species and to perform a comparison on different features types and classifiers. We propose a new features type extracted from raw signals of phytoplankton species. We then analyze the performance of various classifiers on the proposed features type as well as two other features types for finding the robust one. Through experiments, it is found that Random Forest using the proposed features gives the best classification results with average accuracy up to 98.24%.

stat.ML↗