Networks For Image Classification Research Articles

Performance Optimization of Convolutional Neural Networks in Image Classification

With the development of deep learning, CNNs have become mainstream in image classification. However, CNN performance is affected by factors like loss function choice and optimization algorithm. This paper aims to improve CNN performance in image classification by optimizing SGD. Firstly, we analyze different loss functions and propose a suitable optimization strategy. Second, we explore SGD and its variants' roles in CNN training, focusing on accelerating convergence and improving accuracy. Experiments show the proposed scheme effectively enhances CNN performance, providing a reliable solution for image classification. This study supports CNN applications in image recognition and lays a foundation for exploring more efficient optimization methods.

Cnn-assisted multi-hop graph attention network for hyperspectral image classification

ABSTRACT Recently, the convolutional neural network (CNN) has gained widespread adoption in the hyperspectral image (HSI) classification owing to its remarkable feature extraction capability. However, the fixed acceptance domain of CNN restricts it to Euclidean image data only, making it difficult to capture complex information in hyperspectral data. To overcome this problem, much attention has been paid to the graph attention network (GAT), which can effectively model graph structure and capture complex dependencies between nodes. However, GAT usually acts on superpixel nodes, which may lead to the loss of pixel-level information. To better integrate the advantages of both, we propose a CNN-assisted multi-hop graph attention network (CMGAT) for HSI classification. Specifically, a parallel dual-branch architecture is first constructed to simultaneously capture spectral-spatial features from hyperspectral data at the superpixel and pixel levels using GAT and CNN, respectively. On this basis, the multi-hop and multi-scale mechanisms are further employed to construct a multi-hop GAT module and a multi-scale CNN module to capture diverse feature information. Secondly, an attention module is cascaded before the multi-scale CNN module to improve classification performance. Eventually, the output information from the two branches is weighted and fused to produce the classification result. We performed experiments on four benchmark HSI datasets, including Indian Pines (IP), University of Pavia (UP), Salinas Valley (SV) and WHU-Hi-LongKou (LK). The results demonstrate that the proposed method outperforms several deep learning methods, achieving overall accuracies of 95.67%, 99.04%, 99.55% and 99.51%, respectively, even with fewer training samples.

A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification.

Detecting pneumonia, especially coronavirus disease 2019 (COVID-19), from chest X-ray (CXR) images is one of the most effective ways for disease diagnosis and patient triage. The application of deep neural networks (DNNs) for CXR image classification is limited due to the small sample size of the well-curated data. To tackle this problem, this article proposes a distance transformation-based deep forest framework with hybrid-feature fusion (DTDF-HFF) for accurate CXR image classification. In our proposed method, hybrid features of CXR images are extracted in two ways: hand-crafted feature extraction and multigrained scanning. Different types of features are fed into different classifiers in the same layer of the deep forest (DF), and the prediction vector obtained at each layer is transformed to form distance vector based on a self-adaptive scheme. The distance vectors obtained by different classifiers are fused and concatenated with the original features, then input into the corresponding classifier at the next layer. The cascade grows until DTDF-HFF can no longer gain benefits from the new layer. We compare the proposed method with other methods on the public CXR datasets, and the experimental results show that the proposed method can achieve state-of-the art (SOTA) performance. The code will be made publicly available at https://github.com/hongqq/DTDF-HFF.

Out-of-Distribution Detection by Cross-Class Vicinity Distribution of In-Distribution Data.

Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground-truth labels in training without differentiating out-of-distribution samples from in-distribution ones. This results from the assumption that all samples are independent and identically distributed (IID) without distributional distinction. Therefore, a pretrained network learned from in-distribution samples treats out-of-distribution samples as in-distribution and makes high-confidence predictions on them in the test phase. To address this issue, we draw out-of-distribution samples from the vicinity distribution of training in-distribution samples for learning to reject the prediction on out-of-distribution inputs. A cross-class vicinity distribution is introduced by assuming that an out-of-distribution sample generated by mixing multiple in-distribution samples does not share the same classes of its constituents. We, thus, improve the discriminability of a pretrained network by finetuning it with out-of-distribution samples drawn from the cross-class vicinity distribution, where each out-of-distribution input corresponds to a complementary label. Experiments on various in-/out-of-distribution datasets show that the proposed method significantly outperforms the existing methods in improving the capacity of discriminating between in- and out-of-distribution samples.

Weighted Contrastive Prototype Network for Few-Shot Hyperspectral Image Classification with Noisy Labels

Few-shot hyperspectral image classification aims to develop the ability of classifying image pixels by using relatively few labeled pixels per class. However, due to the inaccuracy of the localization system and the bias of the ground survey, the potential noisy labels in the training data pose a very significant challenge to few-shot hyperspectral image classification. To solve this problem, this paper proposes a weighted contrastive prototype network (WCPN) for few-shot hyperspectral image classification with noisy labels. WCPN first utilizes a similarity metric to generate the weights of the samples from the same classes, and applies them to calibrate the class prototypes of support and query sets. Then the weighted prototype network will minimize the distance between features and prototypes to train the network. WCPN also incorporates a weighted contrastive regularization function that uses the sample weights as gates to filter the fake positive samples whose labels are incorrect to further improve the discriminative power of the prototypes. We conduct experiments on multiple hyperspectral image datasets with artificially generated noisy labels, and the results show that the WCPN has excellent performance that can sufficiently mitigate the impact of noisy labels.

PGNN-Net: Parallel Graph Neural Networks for Hyperspectral Image Classification Using Multiple Spatial-Spectral Features

Hyperspectral image (HSI) shows great potential for application in remote sensing due to its rich spectral information and fine spatial resolution. However, the high dimensionality, nonlinearity, and complex relationship between spectral and spatial features of HSI pose challenges to its accurate classification. Traditional convolutional neural network (CNN)-based methods suffer from detail loss in feature extraction; Transformer-based methods rely too much on the quantity and quality of HSI; and graph neural network (GNN)-based methods provide a new impetus for HSI classification by virtue of their excellent ability to handle irregular data. To address these challenges and take advantage of GNN, we propose a network of parallel GNNs called PGNN-Net. The network first extracts the key spatial-spectral features of HSI using principal component analysis, followed by preprocessing to obtain two primary features and a normalized adjacency matrix. Then, a parallel architecture is constructed using improved GCN and ChebNet to extract local and global spatial-spectral features, respectively. Finally, the discriminative features obtained through the fusion strategy are input into the classifier to obtain the classification results. In addition, to alleviate the over-fitting problem, the label smoothing technique is embedded in the cross-entropy loss function. The experimental results show that the average overall accuracy obtained by our method on Indian Pines, Kennedy Space Center, Pavia University Scene, and Botswana reaches 97.35%, 99.40%, 99.64%, and 98.46%, respectively, which are better compared to some state-of-the-art methods.

Empowering informed choices: How computer vision can assists consumers in making decisions about meat quality

Consumers often find it challenging to assess meat sensory quality, influenced by tenderness and intramuscular fat (IMF). This study aims to develop a computer vision system (CVS) using smartphone images to classify beef and pork steak tenderness (1), predicting shear force (SF) and IMF content (2), and performing a comparative evaluation between consumer assessments and the method's output (3). The dataset consisted of 924 beef and 514 pork steaks (one image per steak). We trained a deep neural network for image classification and regression. The model achieved an F1-score of 68.1 % in classifying beef as tender. After re-categorizing the dataset into ‘tender’ and ‘tough’, the F1-score for identifying tender increased to 76.6 %. For pork loin tenderness, the model achieved an F1-score of 81.4 %. This score slightly improved to 81.5 % after re-categorization into two classes. The regression models for predicting SF and IMF in beef steak achieved an R2 value of 0.64 and 0.62, respectively, with a root mean squared prediction error (RMSEP) of 16.9 N and 2.6 %. For pork loin, the neural network predicted SF with an R2 value of 0.76 and an RMSEP of 9.15 N, and IMF with an R2 value of 0.54 and an RMSEP of 1.22 %. In 1000 paired comparisons, the neural network correctly identified the more tender beef steak in 76.5 % of cases, compared to a 46.7 % accuracy rate for human assessments. These findings suggest that CVS can provide a more objective method for evaluating meat tenderness and IMF before purchase, potentially enhancing consumer satisfaction.

Classification of Lung Cancer using Pre-Trained Deep Learning Models

Many Computer Assisted Diagnosis (CAD) systems have been designed and used in recent past for diagnosingdifferenttypes of cancer. Identification of carcinoma at an earlier stage is more important, and it is made possible due to the use modern image processing and deep learning methods.The occurrence of Lung cancer is seen to be increased and Computed Tomography (CT) scan images were utilized in investigation to locate and classify lung cancer, also for determining the severity of those cancer. This study is aimed at employing pre-trained deep neural networks for classification of lung cancer images. A gaussian-based approach is used to segment CT scan images. In this research exploits a transfer learning-based classification method for the chest CT images acquired from Cancer Image Archive and available in the Kaggle platform. Pre- trained models VGG and RESNET were trained using segmented chest CT images, and their performance was evaluated using different optimization algorithms were analyzed. Keywords: Computer Aided Diagnosis, lung cancer, deep learning, CT image, gaussian, transfer learning, pre-trained models, optimization algorithms.

Investigation of the performances of Support Vector Machine, Random Forest, and 3D-2D Convolutional Neural Network for Hyperspectral Image Classification

Classification of the hyperspectral images (HSIs) is one of the most challenging tasks hyperspectral remote sensing. Various Machine Learning classification algorithms have been implemented to HSI classification. In recent years, several Convolutional Neural Network (CNN) architectures were developed for HSI classification. The aim of this study is to test the performance of CNN, and well-known Support Vector Machine and Random Forest algorithms using the HyRANK Loukia, Houston 2013, and Salinas Scene datasets. The findings indicate that the Modified HybridSN CNN outperformed other algorithms across all datasets, as demonstrated by various performance evaluation metrics.

A lightweight parallel attention residual network for tile defect recognition

In modern industrial production, permanent magnet motors are an indispensable part of industrial manufacturing. The quality of the magnetic tiles directly affects the working performance of the permanent magnet motors, making the detection of defects on the surface of magnetic tiles critically important. However, due to the small size of defects on the tile image and the reflectivity of the defective surface, the details of image characteristics are not prominently acquired.These problems bring a lot of difficulties for the recognition of magnetic tile defects. In this paper, a magnetic tile defect detection method is proposed for the probAlems of unclear image features and small defects. First, the image is processed using linear variation to enhance the image detail features. Then, by introducing the inverted bottleneck block structure in MobileNetV2, the Attention Parallel Residual Convolution Block (APR) is proposed, and the Lightweight Parallel Attention Residual Network (LPAR-Net) is built. In APR Block, 7 × 7 convolution is introduced so that the model can extract spatial features from a larger range, and weighted fusion of input images by residual structure. In addition, in this paper, CBAM is improved, split into two parts and inserted into APR Block. Finally, the mainstream image classification models and the LPAR-Net proposed in this paper are used for comparison, respectively. The experimental results show that the method achieves 93.63% accuracy on the adopted dataset, which is better than the existing mainstream image classification network models DenseNet, MobileNet, ConvNext and so on. In addition, this paper introduces a strip steel surface defect dataset and compares it with the above image classification model, which verifies that the detection method proposed in this paper still has strong recognition capability.

Lightweight omni-dimensional dynamic convolution with spatial-spectral self-attention network for hyperspectral image classification

ABSTRACT Omni-dimensional dynamic convolution can adjust spatial sizes, the amount of input/output channels, and kernel size based on the characteristics of the input, thus improving the capacity to extract characteristics through convolution, resulting in increased computation and model complexity. As a result, it is challenging to deploy these models on resource-limited airborne high-spectral testing systems. This paper proposes a lightweight omni-dimensional dynamic convolution network as a possible solution to this issue. In this network, the LS2CM module is used for spatial-spectral information extraction, and the pyramidal residual network is the basic architecture for extracting features from shallow to deep layers, and lightweight omni-dimensional dynamic convolution is adopted in the convolution module. Overcoming the pyramidal structure can only extract local information, we proposed a new simple spatial-spectral self-attention mechanism to extract global information from hyperspectral. Besides, the Huber function as an activation function. The IP, WHU-Hi-LongKou, SA, and PU datasets were used to verify the accuracy of the suggested network model. The results show that the proposed lightweight network maintains an appropriate equilibrium among model complexity as well as accuracy.

A hybrid approach consisting of 3D depthwise separable convolution and depthwise squeeze-and-excitation network for hyperspectral image classification

A hybrid approach consisting of 3D depthwise separable convolution and depthwise squeeze-and-excitation network for hyperspectral image classification

Possibilities of Application of Neuro-Fuzzy Networks for Ophthalmologic Image Classification

Possibilities of Application of Neuro-Fuzzy Networks for Ophthalmologic Image Classification

FBENet: Feature-Level Boosting Ensemble Network for Hashimoto's Thyroiditis Ultrasound Image Classification.

Distinguishing Hashimoto's thyroiditis (HT) lesions from ordinary thyroid tissues is difficult with ultrasound images. Challenges in achieving high performance of HT ultrasound image classification include the low resolution, blurred features and large area of irrelevant noise. To address these problems, we propose a Feature-level Boosting Ensemble Network (FBENet) for HT ultrasound image classification. Specifically, to capture the features of suspicious HT lesions efficiently, an Ensemble Feature Boosting Module (EFBM) is introduced into the feature-level ensemble to boost the blurred features. Then, the spatial attention mechanism is adopted in backbone models to improve the feature focusing performance and representation ability. Furthermore, feature-level ensemble technique is employed in the training process to achieve more comprehensive feature representation ability. Experimentally, FBENet was trained on 6,503 HT ultrasound images, and tested on 1,626 HT ultrasound images with 82.92% accuracy and 89.24% AUC on average.

A semantic guidance-based fusion network for multi-label image classification

Multi-label image classification (MLIC), a fundamental task assigning multiple labels to each image, has been seen notable progress in recent years. Considering simultaneous appearances of objects in the physical world, modeling object correlations is crucial for enhancing classification accuracy. This involves accounting for spatial image feature correlation and label semantic correlation. However, existing methods struggle to establish these correlations due to complex spatial location and label semantic relationships. On the other hand, regarding the fusion of image feature relevance and label semantic relevance, existing methods typically learn a semantic representation in the final CNN layer to combine spatial and label semantic correlations. However, different CNN layers capture features at diverse scales and possess distinct discriminative abilities. To address these issues, in this paper we introduce the Semantic Guidance-Based Fusion Network (SGFN) for MLIC. To model spatial image feature correlation, we leverage the advanced TResNet architecture as the backbone network and employ the Feature Aggregation Module for capturing global spatial correlation. For label semantic correlation, we establish both local and global semantic correlation. We further enrich model features by learning semantic representations across multiple convolutional layers. Our method outperforms current state-of-the-art techniques on PASCAL VOC (2007, 2012) and MS-COCO datasets.

Cross-Hopping Graph Networks for Hyperspectral–High Spatial Resolution (H2) Image Classification

As we take stock of the contemporary issue, remote sensing images are gradually advancing towards hyperspectral–high spatial resolution (H2) double-high images. However, high resolution produces serious spatial heterogeneity and spectral variability while improving image resolution, which increases the difficulty of feature recognition. So as to make the best of spectral and spatial features under an insufficient number of marking samples, we would like to achieve effective recognition and accurate classification of features in H2 images. In this paper, a cross-hop graph network for H2 image classification(H2-CHGN) is proposed. It is a two-branch network for deep feature extraction geared towards H2 images, consisting of a cross-hop graph attention network (CGAT) and a multiscale convolutional neural network (MCNN): the CGAT branch utilizes the superpixel information of H2 images to filter samples with high spatial relevance and designate them as the samples to be classified, then utilizes the cross-hop graph and attention mechanism to broaden the range of graph convolution to obtain more representative global features. As another branch, the MCNN uses dual convolutional kernels to extract features and fuse them at various scales while attaining pixel-level multi-scale local features by parallel cross connecting. Finally, the dual-channel attention mechanism is utilized for fusion to make image elements more prominent. This experiment on the classical dataset (Pavia University) and double-high (H2) datasets (WHU-Hi-LongKou and WHU-Hi-HongHu) shows that the H2-CHGN can be efficiently and competently used in H2 image classification. In detail, experimental results showcase superior performance, outpacing state-of-the-art methods by 0.75–2.16% in overall accuracy.

A multiscale dilated attention network for hyperspectral image classification

Hyperspectral imaging is an image obtained by combining spectral detection technology and imaging technology, which can collect electromagnetic spectra in the wavelength range of visible light to near-infrared. It is an important research content in the field of ground observation in hyperspectral remote sensing. However, hyperspectral image face significant challenges in classification task due to their high spectral dimensions, lack of labeled samples, and strong correlation between bands. In order to fully extract features from both spectral and spatial dimensions and improve classification accuracy in the case of limited training samples, a multiscale dilated attention network is proposed for hyperspectral image classification. First, a three-dimensional convolutional layer is used to extract the shallow features of the image. Then, a multiscale dilated attention module is proposed by combining dilated convolution and channel attention. Using ordinary convolution and dilated convolution to form different receptive fields. Channel attention is used to remodel the obtained multiscale features, enhancing the inter-channel correlation. After that, a multiscale spatial-spectral attention module is constructed using multiple asymmetric convolutions to obtain spatial and spectral attention features at different positions, further enhancing important feature suppression over non-important features. Finally, using softmax to classify the obtained features. Using Indian Pines, Pavia University, KSC and University of Houston as experimental datasets, the overall classification accuracy of this paper’s method achieved 98.97%, 99.14%, 99.45%, and 98.56% respectively, using only 5%, 1%, 10%, and 10% of training samples per class. Compared with seven advanced classification methods, the experimental results show that the proposed method can achieve the highest classification accuracy with limited training samples.

A consistency-aware deep capsule network for hierarchical multi-label image classification

Hierarchical classification is a significant challenge in computer vision due to the logical order and interconnectedness of multiple labels. This paper presents HD-CapsNet, a novel neural network architecture based on deep capsule networks, specifically designed for hierarchical multi-label classification(HMC). By incorporating a tree-like hierarchical structure, HD-CapsNet is designed to leverage the inherent ontological order within the hierarchical label tree, thereby ensuring classification consistency across different levels. Additionally, we introduce a specialized loss function that promotes accurate hierarchical relationships while penalizing inconsistencies. This not only enhances classification performance but also strengthens the network’s robustness. We rigorously evaluate HD-CapsNet’s efficacy by benchmarking it against existing HMC methods across six diverse datasets: Fashion-MNIST, Marine-Tree, CIFAR-10, CIFAR-100, Caltech-UCSD Birds-200-2011, and Stanford Cars. Our results conclusively demonstrate that HD-CapsNet excels in learning hierarchical relationships and significantly outperforms the competition in various image classification tasks. Our implementation is available at https://github.com/tasrif-khondaker/HD-CapsNet.

A local enhanced mamba network for hyperspectral image classification

Deep learning has significantly advanced hyperspectral image (HSI) classification, primarily due to its robust nonlinear feature extraction capabilities. The vision transformer has achieved notable performance but is limited by the quadratic computational burden of its self-attention mechanism. Recently, a network based on state space model named Mamba, has attracted considerable attention for its linear complexity and commendable performance. Nevertheless, Mamba was originally designed for one-dimensional causal sequence modeling, and its effectiveness in inherent non-causal HSI classification remains to be fully validated. To address this issue, we propose a novel Local Enhanced Mamba (LE-Mamba) network for hyperspectral image classification, which mainly comprises a Local Enhanced Spatial SSM (LES-S6), a Central Region Spectral SSM (CRS-S6), and a Multi-Scale Convolutional Gated Unit (MSCGU). The LES-S6 improves non-causal local feature extraction by incorporating a multi-directional local spatial scanning mechanism. Additionally, the CRS-S6 employs a bidirectional scanning mechanism in the spectral dimension to capture fine spectral details and integrate them with spatial information. The MSCGU utilizes a convolutional gating mechanism to aggregate features from diverse scanning routes and extract high-level semantic information. The overall accuracies of LE-Mamba on Indian Pines, WHU-Hi-HanChuan, WHU-Hi-LongKou, and Pavia University datasets are 99.16 %, 98.16 %, 99.57 %, and 99.63 %, respectively. Extensive experimental results on these four public datasets demonstrate that the LE-Mamba outperforms eight mainstream deep learning models in classification performance.

Image Classification Based on Low-Level Feature Enhancement and Attention Mechanism

Deep learning-based image classification networks heavily rely on the extracted features. However, as the model becomes deeper, important features may be lost, resulting in decreased accuracy. To tackle this issue, this paper proposes an image classification method that enhances low-level features and incorporates an attention mechanism. The proposed method employs EfficientNet as the backbone network for feature extraction. Firstly, the Feature Enhancement Module quantifies and statistically processes low-level features from shallow layers, thereby enhancing the feature information. Secondly, the Convolutional Block Attention Module enhances the high-level features to improve the extraction of global features. Finally, the enhanced low-level features and global features are fused to supplement low-resolution global features with high-resolution details, further improving the model’s image classification ability. Experimental results illustrate that the proposed method achieves a Top-1 classification accuracy of 86.49% and a Top-5 classification accuracy of 96.90% on the ETH-Food101 dataset, 86.99% and 97.24% on the VireoFood-172 dataset, and 70.99% and 92.73% on the UEC-256 dataset. These results demonstrate that the proposed method outperforms existing methods in terms of classification performance.