In order to probe into the self-organizing emergence of simple cell orientation selectivity,we tried to construct a neural network model that consists of LGN neurons and simple cells in visual cortex and obeys the Heb...In order to probe into the self-organizing emergence of simple cell orientation selectivity,we tried to construct a neural network model that consists of LGN neurons and simple cells in visual cortex and obeys the Hebbian learning rule. We investigated the neural coding and representation of simple cells to a natural image by means of this model. The results show that the structures of their receptive fields are determined by the preferred orientation selectivity of simple cells.However, they are also decided by the emergence of self-organization in the unsupervision learning process. This kind of orientation selectivity results from dynamic self-organization based on the interactions between LGN and cortex.展开更多
为了更快且更准确地对图像进行识别,提出了基于局部感受野的宽度学习算法(Local Receptive Field based Broad Learning System,BLS-LRF),该方法以宽度学习网(Broad Learning System,BLS)为基础模型,与局部感受野(LRF)的思想相结合,从...为了更快且更准确地对图像进行识别,提出了基于局部感受野的宽度学习算法(Local Receptive Field based Broad Learning System,BLS-LRF),该方法以宽度学习网(Broad Learning System,BLS)为基础模型,与局部感受野(LRF)的思想相结合,从局部特征和全局特征两方面对图像进行特征提取。采用两种图像数据集对网络进行研究,将研究结果和许多传统神经网络进行对比,结果表明BLS-LRF网络的测试精度不仅超过了传统网络的测试精度,而且训练过程所需要的时间有了很大程度的缩短。展开更多
针对轻量化网络结构从特征图提取有效语义信息不足,以及语义信息与空间细节信息融合模块设计不合理而导致分割精度降低的问题,本文提出一种结合全局注意力机制的实时语义分割网络(global attention mechanism with real time semantic s...针对轻量化网络结构从特征图提取有效语义信息不足,以及语义信息与空间细节信息融合模块设计不合理而导致分割精度降低的问题,本文提出一种结合全局注意力机制的实时语义分割网络(global attention mechanism with real time semantic segmentation network,GaSeNet)。首先在双分支结构的语义分支中引入全局注意力机制,在通道与空间两个维度引导卷积神经网来关注与分割任务相关的语义类别,以提取更多有效语义信息;其次在空间细节分支设计混合空洞卷积块,在卷积核大小不变的情况下扩大感受野,以获取更多全局空间细节信息,弥补关键特征信息损失。然后重新设计特征融合模块,引入深度聚合金塔池化,将不同尺度的特征图深度融合,从而提高网络的语义分割性能。最后将所提出的方法在CamVid数据集和Vaihingen数据集上进行实验,通过与最新的语义分割方法对比分析可知,GaSeNet在分割精度上分别提高了4.29%、16.06%,实验结果验证了本文方法处理实时语义分割问题的有效性。展开更多
基金the National Natural Science Foundation of China (Grant Nos. 39893340-06, 69835020, 39670186).
文摘In order to probe into the self-organizing emergence of simple cell orientation selectivity,we tried to construct a neural network model that consists of LGN neurons and simple cells in visual cortex and obeys the Hebbian learning rule. We investigated the neural coding and representation of simple cells to a natural image by means of this model. The results show that the structures of their receptive fields are determined by the preferred orientation selectivity of simple cells.However, they are also decided by the emergence of self-organization in the unsupervision learning process. This kind of orientation selectivity results from dynamic self-organization based on the interactions between LGN and cortex.
文摘为了更快且更准确地对图像进行识别,提出了基于局部感受野的宽度学习算法(Local Receptive Field based Broad Learning System,BLS-LRF),该方法以宽度学习网(Broad Learning System,BLS)为基础模型,与局部感受野(LRF)的思想相结合,从局部特征和全局特征两方面对图像进行特征提取。采用两种图像数据集对网络进行研究,将研究结果和许多传统神经网络进行对比,结果表明BLS-LRF网络的测试精度不仅超过了传统网络的测试精度,而且训练过程所需要的时间有了很大程度的缩短。
文摘针对轻量化网络结构从特征图提取有效语义信息不足,以及语义信息与空间细节信息融合模块设计不合理而导致分割精度降低的问题,本文提出一种结合全局注意力机制的实时语义分割网络(global attention mechanism with real time semantic segmentation network,GaSeNet)。首先在双分支结构的语义分支中引入全局注意力机制,在通道与空间两个维度引导卷积神经网来关注与分割任务相关的语义类别,以提取更多有效语义信息;其次在空间细节分支设计混合空洞卷积块,在卷积核大小不变的情况下扩大感受野,以获取更多全局空间细节信息,弥补关键特征信息损失。然后重新设计特征融合模块,引入深度聚合金塔池化,将不同尺度的特征图深度融合,从而提高网络的语义分割性能。最后将所提出的方法在CamVid数据集和Vaihingen数据集上进行实验,通过与最新的语义分割方法对比分析可知,GaSeNet在分割精度上分别提高了4.29%、16.06%,实验结果验证了本文方法处理实时语义分割问题的有效性。
