SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks

28 Jan 2024  ·  Serdar Erisen ·

Improving the efficiency of state-of-the-art methods in semantic segmentation requires overcoming the increasing computational cost as well as issues such as fusing semantic information from global and local contexts. Based on the recent success and problems that convolutional neural networks (CNNs) encounter in semantic segmentation, this research proposes an encoder-decoder architecture with a unique efficient residual network, Efficient-ResNet. Attention-boosting gates (AbGs) and attention-boosting modules (AbMs) are deployed by aiming to fuse the equivariant and feature-based semantic information with the equivalent sizes of the output of global context of the efficient residual network in the encoder. Respectively, the decoder network is developed with the additional attention-fusion networks (AfNs) inspired by AbM. AfNs are designed to improve the efficiency in the one-to-one conversion of the semantic information by deploying additional convolution layers in the decoder part. Our network is tested on the challenging CamVid and Cityscapes datasets, and the proposed methods reveal significant improvements on the residual networks. To the best of our knowledge, the developed network, SERNet-Former, achieves state-of-the-art results (84.62 % mean IoU) on CamVid dataset and challenging results (87.35 % mean IoU) on Cityscapes validation dataset.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
2D Semantic Segmentation CamVid SERNet-Former mIoU 84.62 # 1
Semantic Segmentation CamVid SERNet-Former Mean IoU 84.62 # 1
Semantic Segmentation Cityscapes test SERNet-Former Mean IoU (class) 84.83 # 7
Semantic Segmentation Cityscapes val SERNet-Former mIoU 87.35 # 1
Validation mIoU 87.35 # 1
2D Semantic Segmentation Cityscapes val SERNet-Former mIoU 87.35 # 1