An Enhanced Encoder-Decoder Network Architecture for Reducing Information Loss in Image Semantic Segmentation

TL;DR

This paper proposes an enhanced encoder-decoder network with residual connections and a modified loss function to reduce information loss and improve accuracy in image semantic segmentation, outperforming traditional architectures like SegNet.

Contribution

Introduces a novel encoder-decoder architecture with multi-residual connections and a balanced loss function to minimize information loss and enhance segmentation accuracy.

Findings

Significant reduction in information loss during sampling.

Improved mean Intersection over Union (mIoU) on benchmark datasets.

Enhanced training convergence and sample imbalance handling.

Abstract

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an innovative encoder-decoder network structure enhanced with residual connections. Our approach employs a multi-residual connection strategy designed to preserve the intricate details across various image scales more effectively, thus minimizing the information loss inherent to down-sampling procedures. Additionally, to enhance the convergence rate of network training and mitigate sample imbalance issues, we have devised a modified cross-entropy loss function incorporating a balancing factor. This modification optimizes the distribution between positive and negative samples, thus improving the efficiency of model training. Experimental evaluations of our model demonstrate a substantial reduction in information loss and improved accuracy in semantic segmentation. Notably, our proposed network architecture demonstrates a substantial improvement in the finely annotated mean Intersection over Union (mIoU) on the dataset compared to the conventional SegNet. The proposed network structure not only reduces operational costs by decreasing manual inspection needs but also scales up the deployment of AI-driven image analysis across different sectors.