Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation

TL;DR

This paper introduces a multi-scale attention U-Net (MsAUNet) that enhances scene segmentation by integrating attention gates and a compound loss function, leading to improved accuracy and faster convergence on standard datasets.

Contribution

The paper presents a novel multi-scale attention mechanism within a modified U-Net architecture and a combined loss function for better scene segmentation performance.

Findings

Achieved 79.88% mean IoU on PascalVOC2012

Achieved 44.88% mean IoU on ADE20k

Outperformed existing models in segmentation accuracy

Abstract

Despite the growing success of Convolution neural networks (CNN) in the recent past in the task of scene segmentation, the standard models lack some of the important features that might result in sub-optimal segmentation outputs. The widely used encoder-decoder architecture extracts and uses several redundant and low-level features at different steps and different scales. Also, these networks fail to map the long-range dependencies of local features, which results in discriminative feature maps corresponding to each semantic class in the resulting segmented image. In this paper, we propose a novel multi-scale attention network for scene segmentation purposes by using the rich contextual information from an image. Different from the original UNet architecture we have used attention gates which take the features from the encoder and the output of the pyramid pool as input and produced out-put is further concatenated with the up-sampled output of the previous pyramid-pool layer and mapped to the next subsequent layer. This network can map local features with their global counterparts with improved accuracy and emphasize on discriminative image regions by focusing on relevant local features only. We also propose a compound loss function by optimizing the IoU loss and fusing Dice Loss and Weighted Cross-entropy loss with it to achieve an optimal solution at a faster convergence rate. We have evaluated our model on two standard datasets named PascalVOC2012 and ADE20k and was able to achieve mean IoU of 79.88% and 44.88% on the two datasets respectively, and compared our result with the widely known models to prove the superiority of our model over them.