Residual Conv-Deconv Grid Network for Semantic Segmentation
This addresses pixel-level semantic labeling for full scene images, but it is incremental as it generalizes existing networks like conv-deconv and U-Net.
The paper tackles the resolution loss problem in semantic image segmentation by proposing GridNet, a CNN architecture with multiple interconnected streams at different resolutions, achieving competitive results on the Cityscapes dataset.
This paper presents GridNet, a new Convolutional Neural Network (CNN) architecture for semantic image segmentation (full scene labelling). Classical neural networks are implemented as one stream from the input to the output with subsampling operators applied in the stream in order to reduce the feature maps size and to increase the receptive field for the final prediction. However, for semantic image segmentation, where the task consists in providing a semantic class to each pixel of an image, feature maps reduction is harmful because it leads to a resolution loss in the output prediction. To tackle this problem, our GridNet follows a grid pattern allowing multiple interconnected streams to work at different resolutions. We show that our network generalizes many well known networks such as conv-deconv, residual or U-Net networks. GridNet is trained from scratch and achieves competitive results on the Cityscapes dataset.