ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation

TL;DR

ReSeg is a novel neural network architecture combining convolutional and recurrent layers to improve semantic segmentation accuracy, leveraging global dependencies and local features, and achieving state-of-the-art results on multiple datasets.

Contribution

This paper introduces ReSeg, a new structured prediction model that extends ReNet for semantic segmentation, integrating convolutional and recurrent layers for better global context understanding.

Findings

Achieved state-of-the-art performance on multiple datasets.

Efficiently combines local features with global dependencies.

Flexible architecture suitable for various segmentation tasks.

Abstract

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally and vertically in both directions, encoding patches or activations, and providing relevant global information. Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features. Upsampling layers follow ReNet layers to recover the original image resolution in the final predictions. The proposed ReSeg architecture is efficient, flexible and suitable for a variety of semantic segmentation tasks. We evaluate ReSeg on several widely-used semantic segmentation datasets: Weizmann Horse, Oxford Flower, and CamVid; achieving state-of-the-art performance. Results show that ReSeg can act as a suitable architecture for semantic segmentation tasks, and may have further applications in other structured prediction problems. The source code and model hyperparameters are available on https://github.com/fvisin/reseg.