A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction

01/22/2017
by   Yoonsik Kim, et al.
0

The inception network has been shown to provide good performance on image classification problems, but there are not much evidences that it is also effective for the image restoration or pixel-wise labeling problems. For image restoration problems, the pooling is generally not used because the decimated features are not helpful for the reconstruction of an image as the output. Moreover, most deep learning architectures for the restoration problems do not use dense prediction that need lots of training parameters. From these observations, for enjoying the performance of inception-like structure on the image based problems we propose a new convolutional network-in-network structure. The proposed network can be considered a modification of inception structure where pool projection and pooling layer are removed for maintaining the entire feature map size, and a larger kernel filter is added instead. Proposed network greatly reduces the number of parameters on account of removed dense prediction and pooling, which is an advantage, but may also reduce the receptive field in each layer. Hence, we add a larger kernel than the original inception structure for not increasing the depth of layers. The proposed structure is applied to typical image-to-image learning problems, i.e., the problems where the size of input and output are same such as skin detection, semantic segmentation, and compression artifacts reduction. Extensive experiments show that the proposed network brings comparable or better results than the state-of-the-art convolutional neural networks for these problems.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

research
11/20/2019

An Inception Inspired Deep Network to Analyse Fundus Images

A fundus image usually contains the optic disc, pathologies and other st...
research
03/25/2020

A New Multiple Max-pooling Integration Module and Cross Multiscale Deconvolution Network Based on Image Semantic Segmentation

To better retain the deep features of an image and solve the sparsity pr...
research
03/09/2017

LesionSeg: Semantic segmentation of skin lesions using Deep Convolutional Neural Network

We present a method for skin lesion segmentation for the ISIC 2017 Skin ...
research
04/02/2021

LiftPool: Bidirectional ConvNet Pooling

Pooling is a critical operation in convolutional neural networks for inc...
research
05/24/2016

Dense CNN Learning with Equivalent Mappings

Large receptive field and dense prediction are both important for achiev...
research
09/02/2020

Convolutional Nonlinear Dictionary with Cascaded Structure Filter Banks

This study proposes a convolutional nonlinear dictionary (CNLD) for imag...
research
05/03/2018

Pixel-wise Attentional Gating for Parsimonious Pixel Labeling

To achieve parsimonious inference in per-pixel labeling tasks with a lim...

Please sign up or login with your details

Forgot password? Click here to reset