A Single Graph Convolution is All You Need: Efficient Grayscale Image Classification

With the recent dramatic increase in the popularity of mobile electronic devices equipped with cameras, there is a growing number of real-world applications for image classification. Nevertheless, some of these real-world applications aim to classify images captured in an unconstrained manner and in complex environments where existing image classification techniques may not perform well. We propose an efficient image classification system that is robust enough to cope with challenging imaging conditions, and demonstrate its effectiveness in the context of classification of real-world images of dumpsters captured by mobile phones in the Indian metropolitan city of Hyderabad. Our system is able to achieve accurate classification of the cleanliness state of the dumpsters despite the challenging uncontrolled urban environment by utilizing a multi-stage approach, where the first stage is the efficient detection of the dumpster, and the second stage is the classification of its state. We analyze the performance of the system and provide comprehensive experimental results on a real-world public dataset.

This paper presents an application study of exploiting fuzzy-rough feature selection (FRFS) techniques in aid of efficient and accurate Mars terrain image classification. The employment of FRFS allows the induction of low-dimensionality feature sets from sample descriptions of feature vectors of a much higher dimensionality. Supported with comparative studies, the work demonstrates that FRFS helps to enhance both the effectiveness and the efficiency of conventional classification systems such as multi-layer perceptrons and K-nearest neighbors, by minimizing redundant and noisy features. This is of particular significance for on-board image classification in future Mars rover missions.

A segmented, and possibly multistage, principal components transformation (PCT) is proposed for efficient hyperspectral remote-sensing image classification and display. The scheme requires, initially, partitioning the complete set of bands into several highly correlated subgroups. After separate transformation of each subgroup, the single-band separabilities are used as a guide to carry out feature selection. The selected features can then be transformed again to achieve a satisfactory data reduction ratio and generate the three most significant components for color display. The scheme reduces the computational load significantly for feature extraction, compared with the conventional PCT. A reduced number of features will also accelerate the maximum likelihood classification process significantly, and the process will not suffer the limitations encountered by trying to use the full set of hyperspectral data when training samples are limited. Encouraging results have been obtained in terms of classification accuracy, speed, and quality of color image display using two airborne visible/infrared imaging spectrometer (AVIRIS) data sets.

Outsourcing an image classification task raises privacy concerns, both from the image provider’s perspective, who wishes to keep their images confidential, and from the classification algorithm provider’s perspective, who wishes to protect the intellectual property of their classifier. We propose EPIC, an efficient private image classification system based on support vector machine (SVM) learning, secure against malicious adversaries. EPIC builds upon transfer learning techniques known from the Machine Learning (ML) literature and minimizes the load on the privacy-preserving part. Our solution is based on Multiparty Computation (MPC), it is 34 times faster than Gazelle (USENIX’18) –the state-of-the-art in private image classification– and it improves the communication cost by 50 times, with a 7% higher accuracy on CIFAR-10 dataset. For the same accuracy as Gazelle achieves on CIFAR-10, EPIC is 700 times faster and the communication cost is reduced by 500 times.

Visual Transformers(ViT) have made remarkable achievements in the field of medical image analysis. However, ViT-based methods have poor classification results on some small-scale medical image classification datasets. Meanwhile, many ViT-based models sacrifice computational cost for superior performance, which is a great challenge in practical clinical applications. In this paper, we propose an efficient medical image classification network based on an alternating mixture of CNN and Transformer tandem, which is called Eff-CTNet. Specifically, the existing ViT-based method still mainly relies on multi-head self-attention (MHSA). Among them, the attention maps of MHSA are highly similar, which leads to computational redundancy. Therefore, we propose a group cascade attention (GCA) module to split the feature maps, which are provided to different attention heads to further improves the diversity of attention and reduce the computational cost. In addition, we propose an efficient CNN (EC) module to enhance the ability of the model and extract the local detail information in medical images. Finally, we connect them and design an efficient hybrid medical image classification network, namely Eff-CTNet. Extensive experimental results show that our Eff-CTNet achieves advanced classification performance with less computational cost on three public medical image classification datasets.

Deep learning-based algorithms can provide state-of-the-art accuracy for remote sensing technologies such as unmanned aerial vehicles (UAVs)/drones, potentially enhancing their remote sensing capabilities for many emergency response and disaster management applications. In particular, UAVs equipped with camera sensors can operating in remote and difficult to access disaster-stricken areas, analyze the image and alert in the presence of various calamities such as collapsed buildings, flood, or fire in order to faster mitigate their effects on the environment and on human population. However, the integration of deep learning introduces heavy computational requirements, preventing the deployment of such deep neural networks in many scenarios that impose low-latency constraints on inference, in order to make mission-critical decisions in real time. To this end, this article focuses on the efficient aerial image classification from on-board a UAV for emergency response/monitoring applications. Specifically, a dedicated Aerial Image Database for Emergency Response applications is introduced and a comparative analysis of existing approaches is performed. Through this analysis a lightweight convolutional neural network architecture is proposed, referred to as EmergencyNet, based on atrous convolutions to process multiresolution features and capable of running efficiently on low-power embedded platforms achieving upto 20x higher performance compared to existing models with minimal memory requirements with less than 1% accuracy drop compared to state-of-the-art models.

This special issue of International Journal of Hybrid Intelligent Systems (IJHIS) published by IOS Press contains a selection of papers presented initially at the RSFDGrC’09 Conference (Rough Sets, Fuzzy Sets, Data Mining and Granular Computing) held in IIT Delhi, India, on December 16–20, 2009. RSFDGrC is the series of international scientific conferences spanning over last 15 years. It investigates the meeting points among the four major areas outlined in its title, with respect to foundations and applications. Five papers included in this special issue are devoted to various aspects of rough sets, fuzzy sets, data mining and granular computing, with a special emphasis on hybrid methodologies for solving theoretical problems and dealing with practical challenges of representing and mining compound data. The first paper, “Facilitating Efficient Mars Terrain Image Classification with Fuzzy-Rough Feature Selection” by Changjing Shang, Dave Barnes and Qiang Shen, presents an application study of exploiting fuzzyrough feature selection (FRFS) techniques in aid of efficient and accurate Mars terrain image classification. The employment of FRFS allows for the induction of low-dimensionality feature sets from sample descriptions of feature vectors of a much higher dimensionality. Supported with comparative studies, the work demonstrates that FRFS helps to enhance both the ef-

Efficient ISAR image classification using MECSM representation

Recently, the semi-supervised graph convolutional network (SSGCN) has been verified effective for hyperspectral image (HSI) classification. However, constrained by the limited training data and spectral uncertainty, the classification performance is remained to be further improved. Moreover, attribute to the massive data, the SSGCN with complex computation is generally too time- and resource-consuming to be applicable in real-time needs. To conquer these issues, we propose an efficient symmetric graph metric learning (SGML) framework by incorporating metric learning into the SSGCN paradigm. Specifically, we first conduct multilevel pixel-to-superpixel projection (P-SP) on the HSI to investigate the multiscale spatial information, where the suitable superpixel numbers are adaptively determined. Then, to extract more expressive representations, we design a new structure denoted as GSvolution, comprising the graph convolution (G-Conv) and a novel self-channel-enhanced convolution (S-Conv), to propagate the labeled and unlabeled graph node information and simultaneously enhance the critical intranode channel features. Finally, the superpixel node features are reprojected to the pixel level (SP-P) so that the distilled multistream features can be integrated to obtain the final decision. Noticeably, this ingenious symmetric mechanism (P-SP and SP-P) can alleviate the spectral variability and facilitate the framework to be an efficient model. Furthermore, in the metric learning module, we propose an innovative metric loss function to enhance the discrimination of the embedding features, i.e., inter class far apart and intraclass close. In the experiments, we demonstrate that the classification capacity of the proposed SGML can surpass the comparators on three benchmark data sets.

Using superpixel- or pixel-based segmentation for efficient green roof digital image classification and rapid estimation of plant species cover

We investigate the problem of combining multiple feature channels for the purpose of efficient image classification. Discriminative kernel based methods, such as SVMs, have been shown to be quite effective for image classification. To use these methods with several feature channels, one needs to combine base kernels computed from them. Multiple kernel learning is an effective method for combining the base kernels. However, the cost of computing the kernel similarities of a test image with each of the support vectors for all feature channels is extremely high. We propose an alternate method, where training data instances are selected, using AdaBoost, for each of the base kernels. A composite decision function, which can be evaluated by computing kernel similarities with respect to only these chosen instances, is learnt. This method significantly reduces the number of kernel computations required during testing. Experimental results on the benchmark UCI datasets, as well as on a challenging painting dataset, are included to demonstrate the effectiveness of our method.

Efficient and accurate medical image classification (MIC) methods face two major challenges: (1) high similarity between images of different disease classes; and (2) generating large medical image datasets for training deep neural networks is challenging due to privacy restrictions and the need for expert ground truth annotations. In this paper, we introduce a novel deep learning method called pre-training grayscale images with supervised learning for MIC (MediMatrix). Instead of pre-training on color ImageNet, our approach uses MediMatrix on grayscale ImageNet. To improve the performance of the network, we introduce ShuffleAttention (SA), a self-attention mechanism. By combining SA with the multiple residual structure (ResSA block) and replacing short-cut connections with dense residual connections between corresponding layers (densepath), our network can dynamically adjust channel attention weights and receive image inputs of different sizes, resulting in improved feature representation and better discrimination of similarities between different categories. MediMatrix effectively classifies X-ray images of rheumatoid arthritis (RA), enabling efficient screening without the need for expert analysis or invasive testing. Through extensive experiments, we demonstrate the superiority of MediMatrix over state-of-the-art methods and that color is not critical for rich natural image classification. Our results highlight the potential of computer-aided diagnosis combined with MediMatrix as a valuable screening tool for early detection and intervention in RA.

LitefusionNet: Boosting the performance for medical image classification with an intelligent and lightweight feature fusion network

Efficient and reliable content-based image retrieval and classification techniques are required for the large image databases. Humans perceive images by breaking the scenes into regions and objects. We, therefore, present a novel approach for extracting color and spatial relationships among image regions. For this, we propose a color spatio-histogram and a bin image which express not only the color distribution but also the spatial information of an image. The system constructs a spatial relationship matrix (SRM) with representative bin pixels of a bin image in order to classify natural images, which define prototypical color and spatial relationships of image regions recurred throughout the image collection. Experiment results show that our scheme performs well for image classification.

In remote-sensing, multi-classifier systems (MCS) have found its use for efficient pixel level image classification. Current challenge faced by the RS community is, classification of very high resolution (VHR) satellite/aerial images. Despite the abundance of data, certain inherent difficulties affect the performance of existing pixel-based models. Hence, the trend for classification of VHR imagery has shifted to object-oriented image analysis (OOIA) which work at object level. We propose a shift of paradigm to object-oriented MCS (OOMCS) for efficient classification of VHR imagery. Our system uses the modern computer vision concept of superpixels for the segmentation stage in OOIA. To this end, we construct a learning-based decision fusion method for integrating the decisions from the MCS at superpixel level for the classification task. Upon detailed experimentation, we show that our method exceeds in performance with respect to a variety of traditional OOIA decision systems. Our method has also empirically outperformed under conditions of two typical artefacts, namely unbalanced samples and high intra-class variance.