The research content of fine-grained image recognition is the problem of sub-category recognition under a broad category. Since fine-grained image classification has the data characteristics of little difference betwe...
详细信息
ISBN:
(数字)9798350352719
ISBN:
(纸本)9798350352726
The research content of fine-grained image recognition is the problem of sub-category recognition under a broad category. Since fine-grained image classification has the data characteristics of little difference between classes and big difference within classes, it becomes a very challenging research task. The key to solving this task is to find the key regions in images and extract effective features from them. Based on the analysis and research of existing fine-grained image classification algorithms and models, this paper introduces a weakly supervised fine-grained classification method that utilizes cutmix data augmentation. SE attention module is introduced to enhance the significant regional features of images, and label smoothing mechanism is used to improve the model generalization ability. Compared with traditional methods on CUB_200_2011 dataset, the experimental results demonstrate that our method achieves improved classification performance.
Fault simulation is a time-consuming process that requires customized methods and techniques to accelerate it. Multi-threading and Multi-core approaches are two promising techniques that can be exploited to accelerate...
详细信息
ISBN:
(纸本)9781665414555
Fault simulation is a time-consuming process that requires customized methods and techniques to accelerate it. Multi-threading and Multi-core approaches are two promising techniques that can be exploited to accelerate the fault simulation process by using different parts of the hardware at the same time. However, an efficient parallelization is obtained only by the refinement of software with respect to the hardware platform. In this paper, a parallel multi-thread fault simulation technique is proposed to accelerate the simulation process on multi-core platforms. In this approach, the gate input values are independently assigned to each thread. Each input value carries the information of several parallel simulation processes. This provides a multithread parallel fault simulation environment. The experimental results show that the proposed technique can efficiently use the hardware platform. In a single-core platform. the proposed technique can reduce the time by 25% while in a dual-core increasing the thread approximately halves the execution time.
Uniform distribution of selected features is one of the important factors in optical image matching. In this paper, an effective scheme is proposed to obtain a uniform distribution of the extracted features. At first,...
详细信息
Inpainting-based compression methods are qualitatively promising alternatives to transform-based codecs, but they suffer from the high computational cost of the inpainting step. This prevents them from being applicabl...
详细信息
ISBN:
(纸本)9781665405409
Inpainting-based compression methods are qualitatively promising alternatives to transform-based codecs, but they suffer from the high computational cost of the inpainting step. This prevents them from being applicable to time-critical scenarios such as real-time inpainting of 4K images. As a remedy, we adapt state-of-the-art numerical algorithms of domain decomposition type to this problem. They decompose the image domain into multiple overlapping blocks that can be inpainted in parallel by means of modern GPUs. In contrast to classical block decompositions such as the ones in JPEG, the global inpainting problem is solved without creating block artefacts. We consider the popular homogeneous diffusion inpainting and supplement it with a multilevel version of an optimised restricted additive Schwarz (ORAS) method that solves the local problems with a conjugate gradient algorithm. This enables us to perform real-time inpainting of 4K colour images on contemporary GPUs, which is substantially more efficient than previous algorithms for diffusion-based inpainting.
In stereo matching, perspective differences in images can cause feature inconsistencies. Traditional stereo matching algorithms compare pixel disparities using local parallel windows transformed by matching costs. How...
详细信息
Head and neck cancer is a complex disease that requires precise treatment planning to minimize the risk of radiation-induced toxicity to critical organs. By precisely defining the borders of important structures, orga...
详细信息
Multi-objective neural architecture search (NAS) algorithms aim to automatically search the neural architecture suitable for different computing power platforms by using multi-objective optimization methods. The LEMON...
详细信息
Deep neural networks (DNNs) require distributed training strategies to deal with large data sizes. TensorFlow is one of the most widely used frameworks that support distributed training. Among the TensorFlow training ...
详细信息
Signal filtering plays an important role in pre-processing procedures used in several application fields. In last years, several methods have been proposed by achieving good results. When large data are given in input...
详细信息
ISBN:
(纸本)9781665464956
Signal filtering plays an important role in pre-processing procedures used in several application fields. In last years, several methods have been proposed by achieving good results. When large data are given in input, performance are likely to get worse. Based on the Savitzky-Golay filter, we have developed, in this paper, a parallel implementation with engaging a multi-core architecture. Experiments and tests highlight the gain of performance in time terms.
Skin cancer is a commonly occurring disease, which affects people of all age groups. Automated detection of skin cancer is needed to decrease the death rate by identifying the diseases at the initial stage. The visual...
详细信息
Skin cancer is a commonly occurring disease, which affects people of all age groups. Automated detection of skin cancer is needed to decrease the death rate by identifying the diseases at the initial stage. The visual inspection during the medical examination of skin lesions is a tedious process as the resemblance among the lesions exists. Recently, imaging-based Computer Aided Diagnosis (CAD) model is widely used to screen and detect the skin cancer. This paper is designed with automated Deep Learning with a class attention layer based CAD model for skin lesion detection and classification known as DLCAL-SLDC. The goal of the DLCAL-SLDC model is to detect and classify the different types of skin cancer using dermoscopic images. During image pre-processing, Dull razor approach-based hair removal and average median filtering-based noise removal processes take place. Tsallis entropy based segmentation technique is applied to detect the affected lesion areas in the dermoscopic images. Also, a DLCAL based feature extractor is used for extracting the features from the segmented lesions using Capsule Network (CapsNet) along with CAL and Adagrad optimizer. The CAL layer incorporated into the CapsNet is intended to capture the discriminative class-specific features to cover the class dependencies and effectively bridge the CapsNet for further process. Finally, the classification is carried out by the Swallow Swarm Optimization (SSO) algorithm based Convolutional Sparse Autoencoder (CSAE) known as SSO-CSAE model. The proposed DLCAL-SLDC technique is validated using a benchmark ISIC dataset. The proposed framework has accomplished promising results with 98.50% accuracy, 94.5% sensitivity and 99.1% specificity over the other methods interms of different measures.
暂无评论