Concentrated-Comprehensive Convolutions for lightweight semantic segmentation

by   Hyojin Park, et al.

The semantic segmentation requires a lot of computational cost. The dilated convolution relieves this burden of complexity by increasing the receptive field without additional parameters. For a more lightweight model, using depth-wise separable convolution is one of the practical choices. However, a simple combination of these two methods results in too sparse an operation which might cause severe performance degradation. To resolve this problem, we propose a new block of Concentrated-Comprehensive Convolution (CCC) which takes both advantages of the dilated convolution and the depth-wise separable convolution. The CCC block consists of an information concentration stage and a comprehensive convolution stage. The first stage uses two depth-wise asymmetric convolutions for compressed information from the neighboring pixels. The second stage increases the receptive field by using a depth-wise separable dilated convolution from the feature map of the first stage. By replacing the conventional ESP module with the proposed CCC module, without accuracy degradation in Cityscapes dataset, we could reduce the number of parameters by half and the number of flops by 35 fastest models. We further applied the CCC to other segmentation models based on dilated convolution and our method achieved comparable or higher performance with a decreased number of parameters and flops. Finally, experiments on ImageNet classification task show that CCC can successfully replace dilated convolutions.


page 1

page 3

page 8


EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation

Due to real-time image semantic segmentation needs on power constrained ...

DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation

As a pixel-level prediction task, semantic segmentation needs large comp...

Augmentations: An Insight into their Effectiveness on Convolution Neural Networks

Augmentations are the key factor in determining the performance of any n...

ExtremeC3Net: Extreme Lightweight Portrait Segmentation Networks using Advanced C3-modules

Designing a lightweight and robust portrait segmentation algorithm is an...

Rotated Ring, Radial and Depth Wise Separable Radial Convolutions

Simple image rotations significantly reduce the accuracy of deep neural ...

BRAIN2DEPTH: Lightweight CNN Model for Classification of Cognitive States from EEG Recordings

Several Convolutional Deep Learning models have been proposed to classif...

FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrays

Both efficient neural networks and hardware accelerators are being explo...

Please sign up or login with your details

Forgot password? Click here to reset