目的图像分类与识别是计算机视觉领域的经典问题,是图像检索、目标识别及视频分析理解等技术的基础。目前,基于深度卷积神经网络(CNN)的模型已经在该领域取得了重大突破,其效果远远超过了传统的基于手工特征的模型。但很多深度模型神经元和参数规模巨大,训练困难。为此根据深度CNN模型和人眼视觉原理,提出并设计了一种深度并行交叉CNN模型(PCCNN模型)。方法该模型在Alex-Net基础上,通过两条深度CNN数据变换流,提取两组深度CNN特征;在模型顶端,经过两次混合交叉,得到1 024维的图像特征向量,最后使用Softmax回归对图像进行分类识别。结果与同类模型相比,该模型所提取的特征更具判别力,具有更好的分类识别性能;在Caltech101上top1识别精度达到63%左右,比VGG16高出近5%,比Goog Le Net高出近10%;在Caltech256上top1识别精度达到46%以上,比VGG16高出近5%,比Goog Le Net高出2.6%。结论 PCCNN模型用于图像分类与识别效果显著,在中等规模的数据集上具有比同类其他模型更好的性能,在大规模数据集上其性能有待于进一步验证;该模型也为其他深度CNN模型的设计提供了一种新的思路,即在控制深度的同时,提取更多的特征信息,提高深度模型性能。
In order to improve the performance of the attribute reduction algorithm to deal with the noisy and uncertain large data, a novel co-evolutionary cloud-based attribute ensemble multi-agent reduction（CCAEMR） algorith...
详细信息
In order to improve the performance of the attribute reduction algorithm to deal with the noisy and uncertain large data, a novel co-evolutionary cloud-based attribute ensemble multi-agent reduction（CCAEMR） algorithm is ***, a co-evolutionary cloud framework is designed under the M apReduce mechanism to divide the entire population into different co-evolutionary subpopulations with a self-adaptive scale. Meanwhile, these subpopulations will share their rewards to accelerate attribute reduction ***, a multi-agent ensemble strategy of co-evolutionary elitist optimization is constructed to ensure that subpopulations can exploit any correlation and interdependency between interacting attribute subsets with reinforcing noise ***, these agents are kept within the stable elitist region to achieve the optimal profit. The experimental results show that the proposed CCAEMR algorithm has better efficiency and feasibility to solve large-scale and uncertain dataset problems with complex noise.
暂无评论