We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hie...We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.展开更多
低分辨率激光图像重构存在色彩视觉效果不佳,结构相似度指数低等问题,因此,设计基于色彩视觉传达的低分辨率激光图像重建方法。引入色彩视觉传达技术,填充图像色彩。采用ANC滤波将幅度作为置信度,结合双边滤波器和幅度值域核函数,设计...低分辨率激光图像重构存在色彩视觉效果不佳,结构相似度指数低等问题,因此,设计基于色彩视觉传达的低分辨率激光图像重建方法。引入色彩视觉传达技术,填充图像色彩。采用ANC滤波将幅度作为置信度,结合双边滤波器和幅度值域核函数,设计自适应双边归一化卷积法,滤波处理图像。采用四通道卷积稀疏编码,重建低分辨率激光图像。结果表明,该方法重建图像的色彩视觉传达效果最佳,饱和度为97.2%,亮度、色相、色彩对比度和锐度分别提高7.0%、20°、3.0和0.05 Line Pairs/MM,并且视区平滑性到达0.96,结构相似度指数为0.97,该方法具备了更好的激光图像重建效果。展开更多
基金Manuscript received February 13, 2016 accepted December 7, 2016. This work was supported by the National Natural Science Foundation of China （61362001, 61661031）, Jiangxi Province Innovation Projects for Postgraduate Funds （YC2016-S006）, the International Postdoctoral Exchange Fellowship Program, and Jiangxi Advanced Project for Post-Doctoral Research Fund （2014KY02）.
基金supported by the National Natural Science Foundation of China (Nos.61806107 and 61702135)。
文摘We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.
文摘低分辨率激光图像重构存在色彩视觉效果不佳,结构相似度指数低等问题,因此,设计基于色彩视觉传达的低分辨率激光图像重建方法。引入色彩视觉传达技术,填充图像色彩。采用ANC滤波将幅度作为置信度,结合双边滤波器和幅度值域核函数,设计自适应双边归一化卷积法,滤波处理图像。采用四通道卷积稀疏编码,重建低分辨率激光图像。结果表明,该方法重建图像的色彩视觉传达效果最佳,饱和度为97.2%,亮度、色相、色彩对比度和锐度分别提高7.0%、20°、3.0和0.05 Line Pairs/MM,并且视区平滑性到达0.96,结构相似度指数为0.97,该方法具备了更好的激光图像重建效果。
