SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks (2024-01-28T00:00:00.000000Z)

TL;DR

This research proposes an encoder-decoder architecture with a unique efficient residual network, Efficient-ResNet, developed with the additional attention-fusion networks (AfNs) inspired by AbM to improve the efficiency in the one-to-one conversion of the semantic information.

Abstract

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.

Authors

Serdar Erişen

1 papers

TL;DR

Abstract

Authors

References65 items

A Systematic Approach to Optimizing Energy-Efficient Automated Systems with Learning Models for Thermal Comfort Control in Indoor Spaces

RFNet: Reverse Fusion Network With Attention Mechanism for RGB-D Indoor Scene Understanding

Joint Correlation and Attention Based Feature Fusion Network for Accurate Visual Tracking

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer

Small-Object Sensitive Segmentation Using Across Feature Map Attention

SwinPA-Net: Swin Transformer-Based Multiscale Feature Pyramid Aggregation Network for Medical Image Segmentation

Real-Time Learning and Monitoring System in Fighting against SARS-CoV-2 in a Private Indoor Environment

kMaX-DeepLab: k-means Mask Transformer

Vision Transformer Adapter for Dense Predictions

Attention Guided Global Enhancement and Local Refinement Network for Semantic Segmentation

IoT-Based Real-Time updating multi-layered learning system applied for a special care context during COVID-19

SAB Net: A Semantic Attention Boosting Framework for Semantic Segmentation

Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention

Improving Semantic Segmentation via Efficient Self-Training

HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation

ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

Contextual Transformer Networks for Visual Recognition

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks

CTNet: Context-Based Tandem Network for Semantic Segmentation

Variational Structured Attention Networks for Deep Visual Representation Learning

Referring Segmentation in Images and Videos With Cross-Modal Self-Attention Network

Guided Attention Inference Network

Covariance Attention for Semantic Segmentation

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation

Real-Time Semantic Segmentation via Spatial-Detail Guided Context Propagation

Hierarchical Multi-Scale Attention for Semantic Segmentation

ResNeSt: Split-Attention Networks

EfficientPS: Efficient Panoptic Segmentation

Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks

Image Segmentation Using Deep Learning: A Survey

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

Object-Contextual Representations for Semantic Segmentation

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Improving Semantic Segmentation via Video Propagation and Label Relaxation

CCNet: Criss-Cross Attention for Semantic Segmentation

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

PSANet: Point-wise Spatial Attention Network for Scene Parsing

Self-Supervised Model Adaptation for Multimodal Semantic Segmentation

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

Deep Spatio-Temporal Random Fields for Efficient Video Segmentation

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Squeeze-and-Excitation Networks

Rethinking Atrous Convolution for Semantic Image Segmentation

Pyramid Scene Parsing Network

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Aggregated Residual Transformations for Deep Neural Networks

The Cityscapes Dataset for Semantic Urban Scene Understanding

Deep Residual Learning for Image Recognition

Multi-Scale Context Aggregation by Dilated Convolutions

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling

Highway Networks

Semantic object classes in video: A high-definition ground truth database

Segmentation and Recognition Using Structure from Motion Point Clouds

Image Segmentation

RTLNet: Recursive Triple-Path Learning Network for Scene Parsing of RGB-D Images

The devil is in the labels: Semantic segmentation from sentences

PointMTL: Multi-Transform Learning for Effective 3D Point Cloud Representations

MapSegNet: A Fully Automated Model Based on the Encoder-Decoder Architecture for Indoor Map Segmentation

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

2019 IEEE/CVF International Conference on Computer Vision (ICCV) , Seoul, Korea (South)

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names