A novel method for feature fusion in convolutional neural networks is proposed in this paper. Different feature fusion techniques are suggested to facilitate the flow of information and improve the training of deep neural networks. Some of these techniques as well as the proposed network can be considered a type of Directed Acyclic Graph (DAG) Network, where a layer can receive inputs from other layers and have outputs to other layers. In the proposed general framework of Lattice Fusion Network (LFNet), feature maps of each convolutional layer are passed to other layers based on a lattice graph structure, where nodes are convolutional layers. To evaluate the performance of the proposed architecture, different designs based on the general framework of LFNet are implemented for the task of image denoising. This task is used as an example where training deep convolutional networks is needed. Results are compared with state of the art methods. The proposed network is able to achieve better results with far fewer learnable parameters, which shows the effectiveness of LFNets for training of deep neural networks.
翻译:本文建议了一种新型的方法,用于在进化神经网络中进行特征融合。提出了不同的聚合技术,以便利信息流动,改进深神经网络的培训。其中一些技术以及拟议的网络可以被视为一种类型的定向环形图(DAG)网络,在这个网络中,一个层可以从其他层次获得投入,并可以输出到其他层次。在Lattice 融合网络(LFNet)的拟议总体框架内,每个进化层的地貌图被传送到基于拉蒂斯图结构的其他层次,其中节点是共层。为了评估拟议的结构的性能,根据LFNet的总框架对图像进行分解工作实施了不同的设计。这一任务被用作需要培训深进化网络的范例。结果与艺术方法的状态进行比较。拟议的网络能够以远为少的可学习参数取得更好的结果,这些参数表明LFNet在深神经网络培训方面的有效性。