Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation

• URL: http://arxiv.org/abs/2506.10489v1
• Date: Thu, 12 Jun 2025 08:45:58 GMT
• Title: Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation
• Authors: Guyang Zhang, Waleed Abdulla,
• Abstract summary: It is impractical to collect all the varieties of honey products at once to train a model for botanical origin differentiation.<n>This study examined and compared multiple CIL algorithms on a real-world honey hyperspectral imaging dataset.<n>A novel technique is also proposed to improve the performance of class-incremental learning algorithms by combining with a continual backpropagation (CB) algorithm.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Honey is an important commodity in the global market. Honey types of different botanical origins provide diversified flavors and health benefits, thus having different market values. Developing accurate and effective botanical origin-distinguishing techniques is crucial to protect consumers' interests. However, it is impractical to collect all the varieties of honey products at once to train a model for botanical origin differentiation. Therefore, researchers developed class-incremental learning (CIL) techniques to address this challenge. This study examined and compared multiple CIL algorithms on a real-world honey hyperspectral imaging dataset. A novel technique is also proposed to improve the performance of class-incremental learning algorithms by combining with a continual backpropagation (CB) algorithm. The CB method addresses the issue of loss-of-plasticity by reinitializing a proportion of less-used hidden neurons to inject variability into neural networks. Experiments showed that CB improved the performance of most CIL methods by 1-7\%.

Related papers

• A Multi-Scale Feature Extraction and Fusion Deep Learning Method for Classification of Wheat Diseases [4.8117894377430925]
  This study introduces an innovative approach that integrates multi-scale feature extraction with advanced image segmentation techniques to enhance classification accuracy.<n>The proposed method uses neural network models Xception, Inception V3, and ResNet 50 to train on a large wheat disease classification dataset 2020.<n>The study shows that the suggested methodology has a superior accuracy of 99.75% in the classification of wheat diseases when compared to current state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-17T03:29:41Z)
• Artificial Liver Classifier: A New Alternative to Conventional Machine Learning Models [4.395397502990339]
  This paper introduces the Artificial Liver (ALC), a novel supervised learning classifier inspired by the human liver's detoxification function.<n>The ALC is characterized by its simplicity, speed, hyperparameters-free, ability to reduce overfitting, and effectiveness in addressing multi-classification problems.<n>It was evaluated on five benchmark machine learning datasets: Iris Flower, Breast Cancer Wisconsin, Wine, Voice Gender, and MNIST.
  arXiv  Detail & Related papers  (2025-01-14T12:42:01Z)
• Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling [53.7117640028211]
  We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues. We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space. A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
  arXiv  Detail & Related papers  (2024-03-02T00:56:05Z)
• Unmasking honey adulteration : a breakthrough in quality assurance through cutting-edge convolutional neural network analysis of thermal images [0.0]
  Honey is susceptible to adulteration, a situation that has substantial consequences for the well-being of the general population and the financial well-being of a country. This paper presents a novel approach by employing Convolutional Neural Networks (CNNs) for the classification of honey samples based on thermal images. We have implemented a more streamlined and less complex convolutional neural network (CNN) model, outperforming comparable models with an outstanding accuracy rate of 99%.
  arXiv  Detail & Related papers  (2024-02-12T23:33:22Z)
• An Efficient Transfer Learning-based Approach for Apple Leaf Disease Classification [0.0]
  This study presents a technique for identifying apple leaf diseases based on transfer learning. The competence of the proposed pipeline has been evaluated on the apple leaf disease subset from the publicly available PlantVillage' dataset.
  arXiv  Detail & Related papers  (2023-04-10T08:48:36Z)
• Self-accumulative Vision Transformer for Bone Age Assessment Using the Sauvegrain Method [3.5814626468819046]
  This study presents a novel approach to bone age assessment (BAA) using a multi-view, multi-task classification model based on the Sauvegrain method. A self-accumulative vision transformer (SAT) that mitigates anisotropic behavior is proposed.
  arXiv  Detail & Related papers  (2023-03-29T09:26:54Z)
• Drug Synergistic Combinations Predictions via Large-Scale Pre-Training and Graph Structure Learning [82.93806087715507]
  Drug combination therapy is a well-established strategy for disease treatment with better effectiveness and less safety degradation. Deep learning models have emerged as an efficient way to discover synergistic combinations. Our framework achieves state-of-the-art results in comparison with other deep learning-based methods.
  arXiv  Detail & Related papers  (2023-01-14T15:07:43Z)
• Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images [57.42492501915773]
  In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Human fatigue plays a role in error making, making the use of deep learning appealing. We propose Seamless Iterative Semi-Supervised correction of Imperfect labels (SISSI) Our method successfully provides an adaptive early learning correction technique for object detection.
  arXiv  Detail & Related papers  (2022-08-05T18:52:20Z)
• Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor [55.9023096444383]
  Current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning.
  arXiv  Detail & Related papers  (2022-04-28T08:41:51Z)
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
  Deep neural networks suffer from catastrophic forgetting when learning new categories. We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
  arXiv  Detail & Related papers  (2022-04-10T11:38:33Z)
• Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis [64.82680813427054]
  Plant diseases serve as one of main threats to food security and crop production. One popular approach is to transform this problem as a leaf image classification task, which can be addressed by the powerful convolutional neural networks (CNNs) We propose a novel framework that incorporates rectified meta-learning module into common CNN paradigm to train a noise-robust deep network without using extra supervision information.
  arXiv  Detail & Related papers  (2020-03-17T09:51:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.