Efficient Semantic Segmentation

Efficient semantic segmentation aims to accurately classify each pixel in an image while minimizing computational resources, crucial for real-time applications like autonomous driving and robotics. Current research focuses on developing lightweight architectures, often hybridizing convolutional neural networks (CNNs) with transformers, and employing techniques like token reduction, knowledge distillation, and adaptive resolution strategies to improve efficiency without sacrificing accuracy. These advancements are significant because they enable the deployment of high-performing semantic segmentation models on resource-constrained devices, expanding the practical applicability of this technology across various domains.

Papers

October 3, 2024

Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network
Yangyang Qiu, Guoan Xu, Guangwei Gao, Zhenhua Guo, Yi Yu, Chia-Wen Lin
Convolutional Neural Network Lightweight High Real Time Semantic Segmentation Efficient Semantic Segmentation

August 14, 2024

MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
Beoungwoo Kang, Seunghun Moon, Yubin Cho, Hyunwoo Yu, Suk-Ju Kang
Semantic Segmentation Efficient Semantic Segmentation Context Aware Network

July 24, 2024

Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
Hyunwoo Yu, Yubin Cho, Beoungwoo Kang, Seunghun Moon, Kyeongbo Kong, Suk-Ju Kang
Semantic Segmentation Attention Based Encoder Decoder Efficient Semantic Segmentation Attention Decoder Parameter Free Attention Spatial Inference Free Transformer

June 14, 2024

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
Narges Norouzi, Svetlana Orlova, Daan de Geus, Gijs Dubbelman
Adaptive Importance Semantic Segmentation Network Segmentation Quality Online Merging Token Merging Efficient Semantic Segmentation Plain Vision Transformer Token Reduction

May 17, 2024

CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation
Mushui Liu, Jun Dan, Ziqian Lu, Yunlong Yu, Yingming Li, Xi Li
Semantic Segmentation UNet Based Convolutional Encoder Remote Sensing Image Semantic Segmentation Efficient Semantic Segmentation Mamba UNet Segmentation Decoder Large Scale Remote Sensing Image

May 10, 2024

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
Zhenliang Ni, Xinghao Chen, Yingjie Zhai, Yehui Tang, Yunhe Wang
Semantic Segmentation Self Calibration Efficient Semantic Segmentation Feature Reconstruction

December 11, 2023

U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation
Seul-Ki Yeom, Julian von Klitzing
U Net Transformer Decoder Efficient Semantic Segmentation Transformer Based UNet Mixture of Attention U MixFormer Outperforms SegFormer Multi Scale Context

December 7, 2023

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation
Jiawei Fan, Chao Li, Xiaolong Liu, Meina Song, Anbang Yao
Contrastive Learning Contrastive Loss Contrastive Distillation Efficient Semantic Segmentation

October 30, 2023

Resource Constrained Semantic Segmentation for Waste Sorting
Elisa Cascina, Andrea Pellegrino, Lorenzo Tozzi
Cross Entropy Loss Efficient Waste Efficient Semantic Segmentation Edge Application

October 19, 2023

Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers
Yuanduo Hong, Jue Wang, Weichao Sun, Huihui Pan
Semantic Segmentation Masked Image Modeling Efficient Semantic Segmentation Plain Vision Transformer Non Hierarchical Vision Transformer

September 28, 2023

Superpixel Transformers for Efficient Semantic Segmentation
Alex Zihao Zhu, Jieru Mei, Siyuan Qiao, Hang Yan, Yukun Zhu, Liang-Chieh Chen, Henrik Kretzschmar
Semantic Segmentation Adjacent Superpixels Efficient Semantic Segmentation

June 13, 2023

Efficient 3D Semantic Segmentation with Superpoint Transformer
Damien Robert, Hugo Raguet, Loic Landrieu
3D Semantic Segmentation Efficient Semantic Segmentation SuperPoint Matching Edge Transformer

June 3, 2023

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers
Chenyang Lu, Daan de Geus, Gijs Dubbelman
Vision Transformer Semantic Segmentation Semantic Segmentation Network Segmentation Quality Efficient Semantic Segmentation Token Optimization Segmentation Decoder

March 13, 2023

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos
Yubin Hu, Yuze He, Yanghao Li, Jisheng Li, Yuxing Han, Jiangtao Wen, Yong-Jin Liu
Semantic Segmentation Conjunct ReSolution Compressed Video Efficient Semantic Segmentation High Frame Rate Q Seg Segmentation Backbone

December 28, 2022

Efficient Semantic Segmentation on Edge Devices
Farshad Safavi, Irfan Ali, Venkatesh Dasari, Guanqun Song, Ting Zhu, Maryam Rahnemoonfar
Semantic Segmentation Edge Device Real Time Semantic Segmentation Efficient Semantic Segmentation Two Stage UNet

July 7, 2022

Entropy-Based Feature Extraction For Real-Time Semantic Segmentation
Lusine Abrahamyan, Nikos Deligiannis
Convolutional Neural Network Feature Extraction Patch Based Real Time Semantic Segmentation Efficient Semantic Segmentation

June 16, 2022

Simple and Efficient Architectures for Semantic Segmentation
Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia, Shubhankar Borse, Fatih Porikli, Amirhossein Habibian, Tijmen Blankevoort
Semantic Segmentation Receptive Field Efficient Architecture Efficient Semantic Segmentation

February 27, 2022

TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation
Ruiping Liu, Kailun Yang, Alina Roitberg, Jiaming Zhang, Kunyu Peng, Huayao Liu, Yaonan Wang, Rainer Stiefelhagen
Knowledge Distillation Semantic Segmentation Benchmark Patch Transformer Efficient Semantic Segmentation Large Pre Trained Transformer

November 24, 2021

Towards an Efficient Semantic Segmentation Method of ID Cards for Verification Systems
Rodrigo Lara, Andres Valenzuela, Daniel Schulz, Juan Tapia, Christoph Busch
Semantic Segmentation Identity Verification Efficient Semantic Segmentation

November 18, 2021

Dynamically pruning segformer for efficient semantic segmentation
Haoli Bai, Hongda Mao, Dinesh Nair
Semantic Segmentation Transformer Based Model Efficient Semantic Segmentation U MixFormer Outperforms SegFormer

Efficient Semantic Segmentation

Papers

Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network

MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation

Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers

CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation

Resource Constrained Semantic Segmentation for Waste Sorting

Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers

Superpixel Transformers for Efficient Semantic Segmentation

Efficient 3D Semantic Segmentation with Superpoint Transformer

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos

Efficient Semantic Segmentation on Edge Devices

Entropy-Based Feature Extraction For Real-Time Semantic Segmentation

Simple and Efficient Architectures for Semantic Segmentation

TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation

Towards an Efficient Semantic Segmentation Method of ID Cards for Verification Systems

Dynamically pruning segformer for efficient semantic segmentation