Lattice Fusion Networks for Image Denoising

TL;DR

This paper introduces Lattice Fusion Networks (LFNet), a new feature fusion framework for deep CNNs that improves image denoising performance with fewer parameters by leveraging a lattice graph structure for feature map passing.

Contribution

The paper proposes a novel LFNet framework utilizing lattice graph-based feature fusion, enhancing deep CNN training efficiency and denoising accuracy.

Findings

Achieves better denoising results than state-of-the-art methods.

Uses fewer learnable parameters than comparable models.

Demonstrates effective feature flow via lattice graph structure.

Abstract

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.