Search

Hyperspectral remote sensing technology is swiftly evolving, prioritizing affordability, enhanced portability, seamless integration, sophisticated intelligence, and immediate processing capabilities. The leading model for classifying hyperspectral images, which relies on convolutional neural networks (CNNs), has proven to be highly effective when run on advanced computing platforms. Nonetheless, the high degree of parameterization inherent in CNN models necessitates considerable computational and storage resources, posing challenges to their deployment in processors with limited capacity like drones and satellites. This paper focuses on advancing lightweight models for hyperspectral image classification and introduces EBCNN, a novel binary convolutional neural network. EBCNN is designed to effectively regulate backpropagation gradients and minimize gradient discrepancies to optimize BNN performance. EBCNN incorporates an adaptive gradient scaling module that utilizes a multi-scale pyramid squeeze attention (PSA) mechanism during the training phase, which can adjust training gradients flexibly and efficiently. Additionally, to address suboptimal training issues, EBCNN employs a dynamic curriculum learning strategy underpinned by a confidence-aware loss function, Superloss, enabling progressive binarization and enhancing its classification effectiveness. Extensive experimental evaluations conducted on five esteemed public datasets confirm the effectiveness of EBCNN. These analyses highlight a significant enhancement in the classification accuracy of hyperspectral images, achieved without incurring additional memory or computational overheads during the inference process.

This paper proposes the “ultimate compression” method as a solution to the expansive computation and high storage costs required by state-of-the-art neural network models in inference. Our approach uniquely combines tensor decomposition techniques with binary neural networks to create efficient deep neural network models optimized for edge inference. The process includes training floating-point models, applying tensor decomposition algorithms, binarizing the decomposed layers, and fine tuning the resulting models. We evaluated our approach in various state-of-the-art deep neural network architectures on multiple datasets, such as MNIST, CIFAR-10, CIFAR-100, and ImageNet. Our results demonstrate compression ratios of up to 169×, with only a small degradation in accuracy (1–2%) compared to binary models. We employed different optimizers for training and fine tuning, including Adam and AdamW, and used norm grad clipping to address the exploding gradient problem in decomposed binary models. A key contribution of this work is a novel layer sensitivity-based rank selection algorithm for tensor decomposition, which outperforms existing methods such as random selection and Variational Bayes Matrix Factorization (VBMF). We conducted comprehensive experiments using six different models and present a case study on crowd-counting applications, demonstrating the practical applicability of our method. The ultimate compression method outperforms binary neural networks and tensor decomposition when applied individually in terms of storage and computation costs. This positions it as one of the most effective options for deploying compact and efficient models in edge devices with limited computational resources and energy constraints.

The evolution of super-resolution (SR) technology has seen significant advancements through the adoption of deep learning methods. However, the deployment of such models by resource-constrained devices necessitates models that not only perform efficiently, but also conserve computational resources. Binary neural networks (BNNs) offer a promising solution by minimizing the data precision to binary levels, thus reducing the computational complexity and memory requirements. However, for BNNs, an effective architecture is essential due to their inherent limitations in representing information. Designing such architectures traditionally requires extensive computational resources and time. With the advancement in neural architecture search (NAS), differentiable NAS has emerged as an attractive solution for efficiently crafting network structures. In this paper, we introduce a novel and efficient binary network search method tailored for image super-resolution tasks. We adapt the search space specifically for super resolution to ensure it is optimally suited for the requirements of such tasks. Furthermore, we incorporate Libra Parameter Binarization (Libra-PB) to maximize information retention during forward propagation. Our experimental results demonstrate that the network structures generated by our method require only a third of the parameters, compared to conventional methods, and yet deliver comparable performance.

As is well-known, defects precisely affect the lives and functions of the machines in which they occur, and even cause potentially catastrophic casualties. Therefore, quality assessment before mounting is an indispensable requirement for factories. Apart from the recognition accuracy, current networks suffer from excessive computing complexity, making it of great difficulty to deploy in the manufacturing process. To address these issues, this paper introduces binary networks into the area of surface defect detection for the first time, for the reason that binary networks prohibitively constrain weight and activation to +1 and −1. The proposed Bi-ShuffleNet and U-BiNet utilize binary convolution layers and activations in low bitwidth, in order to reach comparable performances while incurring much less computational cost. Extensive experiments are conducted on real-life NEU and Magnetic Tile datasets, revealing the least OPs required and little accuracy decline. When classifying the defects, Bi-ShuffleNet yields comparable results to counterpart networks, with at least 2× inference complexity reduction. Defect segmentation results indicate similar observations. Some network design rules in defect detection and binary networks are also summarized in this paper.

Neural networks have been widely used and implemented on various hardware platforms, but high computational costs and low similarity of network structures relative to hardware structures are often obstacles to research. In this paper, we propose a novel neural network in combination with the structural features of a recently proposed memory-based programmable logic device, compare it with the standard structure, and test it on common datasets with full and binary precision, respectively. The experimental results reveal that the new structured network can provide almost consistent full-precision performance and binary-precision performance ranging from 61.0% to 78.8% after using sparser connections and about 50% reduction in the size of the weight matrix.

With the advent of the Internet of Everything, more and more devices are connected to the Internet every year. In major cities, in order to maintain normal social order, the demand for deployed cameras is also increasing. In terms of public safety, person Re-Identification (ReID) can play a big role. However, the current methods of ReID are to transfer the collected pedestrian images to the cloud for processing, which will bring huge communication costs. In order to solve this problem, we combine the recently emerging edge computing and use the edge to combine the end devices and the cloud to implement our proposed binarized segmented ResNet. Our method is mainly to divide a complete ResNet into three parts, corresponding to the end devices, the edge, and the cloud. After joint training, the corresponding segmented sub-network is deployed to the corresponding side, and inference is performed to realize ReID. In our experiments, we compared some traditional ReID methods in terms of accuracy and communication overhead. It can be found that our method can greatly reduce the communication cost on the basis of basically not reducing the recognition accuracy of ReID. In general, the communication cost can be reduced by four to eight times.