ICNet for Real-Time Semantic Segmentation on High-Resolution Images
Not on the map. Why?
Abstract (arXiv)
We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion unit to quickly achieve high-quality segmentation. Our system yields real-time inference on a single GPU card with decent quality results evaluated on challenging datasets like Cityscapes, CamVid and COCO-Stuff.
Key facts. Cited by 261 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 72; 2022: 70; 2023: 52; 2024: 33; 2025: 22; 2026: 12.
261 papers.
Sort:
By area:
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
- 2023Segment Anything in High Qualitycited by 373
- 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
- 2022Understanding The Robustness in Vision Transformerscited by 144
- 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
- 2023Transformer-Based Visual Segmentation: A Surveycited by 124
- 2022Cross-Image Relational Knowledge Distillation for Semantic Segmentationcited by 117
- 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
- 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
- 2022Highly Accurate Dichotomous Image Segmentationcited by 110
- 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
38 more
- 2021SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentationcited by 106
- 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
- 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
- 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
- 2022PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllerscited by 84
- 2022TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentationcited by 82
- 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
- 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
- 2021Token Pooling in Vision Transformerscited by 68
- 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
- 2022PODA: Prompt-driven Zero-shot Domain Adaptationcited by 60
- 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
- 2021Capturing Omni-Range Context for Omnidirectional Segmentationcited by 49
- 2021Enhanced Boundary Learning for Glass-like Object Segmentationcited by 48
- 20213D-to-2D Distillation for Indoor Scene Parsingcited by 47
- 2021Deep Reinforcement Learning in Computer Vision: A Comprehensive Surveycited by 42
- 2022EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Predictioncited by 42
- 2023You Only Segment Once: Towards Real-Time Panoptic Segmentationcited by 40
- 2023EdgeSAM: Prompt-In-the-Loop Distillation for SAMcited by 40
- 2023See, Say, and Segment: Teaching LMMs to Overcome False Premisescited by 40
- 2021Progressive Semantic Segmentationcited by 35
- 2023Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detectedcited by 34
- 2023Structural and Statistical Texture Knowledge Distillation for Semantic Segmentationcited by 34
- 2021PaddleSeg: A High-Efficient Development Toolkit for Image Segmentationcited by 33
- 2022PP-LiteSeg: A Superior Real-Time Semantic Segmentation Modelcited by 33
- 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
- 2021High Quality Segmentation for Ultra High-resolution Imagescited by 31
- 2022RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformercited by 31
- 2021Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real Worldcited by 30
- 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
- 2021Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Imagescited by 28
- 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Processcited by 28
- 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
- 2021Local Memory Attention for Fast Video Semantic Segmentationcited by 25
- 2021Smart at what cost? Characterising Mobile Deep Neural Networks in the wildcited by 25
- 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
- 2024CoReS: Orchestrating the Dance of Reasoning and Segmentationcited by 25
- 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
50 most cited of 261 All 261 (JSON)
- 2026CoordFormer: Give Me Any Coordinates and I Will Give You Labels8 Sep 2026
- 2026Real-Time Semantic Segmentation with Optimized RetinaNet Architectures for Embedded Automotive Systems21 Jul 2026
- 2026PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance26 May 2026
- 2026ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion25 May 2026
- 2026SFR-Net: Learning Scale-Frustum Representations for Ultra-Wide Area Remote Sensing Image Segmentation25 May 2026
- 2026OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization19 May 2026
- 2026Sapiens223 Apr 2026
- 2026From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving18 Mar 2026
- 2026PEPR: Privileged Event-based Predictive Regularization for Domain Generalization4 Feb 2026
- 2026Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping16 Jan 2026
- 2026WeedRepFormer: Reparameterizable Vision Transformers for Real-Time Waterhemp Segmentation and Gender Classification6 Jan 2026
- 2026Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation3 Jan 2026
38 more
- 2025Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues7 Dec 2025
- 2025FedDSR: Federated Deep Supervision and Regularization Towards Autonomous Driving7 Dec 2025
- 2025ArmFormer: Lightweight Transformer Architecture for Real-Time Multi-Class Weapon Segmentation and Classification19 Oct 2025
- 2025BlurBall: Joint Ball and Motion Blur Estimation for Table Tennis Ball Tracking22 Sep 2025
- 2025GasTwinFormer: A Hybrid Vision Transformer for Livestock Methane Emission Segmentation and Dietary Classification in Optical Gas Imaging20 Aug 2025
- 2025TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform17 Aug 2025
- 2025A Novel Downsampling Strategy Based on Information Complementarity for Medical Image Segmentation20 Jul 2025
- 2025A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation24 Jun 2025
- 2025A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects16 Jun 2025
- 2025RS-MTDF: Multi-Teacher Distillation and Fusion for Remote Sensing Semi-Supervised Semantic Segmentation10 Jun 2025
- 2025ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network10 Jun 2025
- 2025F2Net: A Frequency-Fused Network for Ultra-High Resolution Remote Sensing Segmentation9 Jun 2025
- 2025SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation28 Apr 2025
- 2025Segregation and Context Aggregation Network for Real-time Cloud Segmentation19 Apr 2025
- 2025Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions2 Apr 2025
- 2025Co-SemDepth: Fast Joint Semantic Segmentation and Depth Estimation on Aerial Images23 Mar 2025
- 2025Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation11 Mar 2025
- 2025Golden Cudgel Network for Real-Time Semantic Segmentation5 Mar 2025
- 2025Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness28 Feb 2025
- 2025Cross-Model Transferability of Adversarial Patches in Real-time Segmentation for Autonomous Driving22 Feb 2025
- 2025PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization11 Feb 2025
- 2025ContextFormer: Redefining Efficiency in Semantic Segmentation31 Jan 2025
- 2024EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality22 Nov 2024
- 2024OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing5 Nov 2024
- 2024Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editing1 Nov 2024
- 2024Domain Adaptation with a Single Vision-Language Embedding28 Oct 2024
- 2024Development and Testing of a Wood Panels Bark Removal Equipment Based on Deep Learning15 Oct 2024
- 2024Multimodal Perception System for Real Open Environment10 Oct 2024
- 2024Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network3 Oct 2024
- 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation30 Sep 2024
- 2024Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack27 Aug 2024
- 2024Freehand Sketch Generation from Mechanical Components12 Aug 2024
- 2024Leveraging Adaptive Implicit Representation Mapping for Ultra High-Resolution Image Segmentation31 Jul 2024
- 2024Sparse Refinement for Efficient High-Resolution Semantic Segmentation26 Jul 2024
- 2024Region Guided Attention Network for Retinal Vessel Segmentation22 Jul 2024
- 2024HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation10 Jul 2024
- 2024Relative Difficulty Distillation for Semantic Segmentation4 Jul 2024
- 2024Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model27 Jun 2024
50 newest of 261 All 261 (JSON)
- 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
- 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Processcited by 28
- 2023Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Modelscited by 22
- 2023Denoising Diffusion Semantic Segmentation with Mask Prior Modelingcited by 15
- 2024Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editingcited by 2
- 2024Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editing1 Nov 2024
- 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?10 Mar 2024
- 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process19 Dec 2023
- 2023Denoising Diffusion Semantic Segmentation with Mask Prior Modeling2 Jun 2023
- 2023Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models23 Mar 2023
- 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
- 2024CoReS: Orchestrating the Dance of Reasoning and Segmentationcited by 25
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2023Segment Anything in High Qualitycited by 373
- 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
- 2022Understanding The Robustness in Vision Transformerscited by 144
- 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
- 2023Transformer-Based Visual Segmentation: A Surveycited by 124
- 2022Cross-Image Relational Knowledge Distillation for Semantic Segmentationcited by 117
- 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
- 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
- 2022Highly Accurate Dichotomous Image Segmentationcited by 110
- 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
- 2021SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentationcited by 106
12 most cited of 247 All 247 (JSON)
- 2026CoordFormer: Give Me Any Coordinates and I Will Give You Labels8 Sep 2026
- 2026Real-Time Semantic Segmentation with Optimized RetinaNet Architectures for Embedded Automotive Systems21 Jul 2026
- 2026PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance26 May 2026
- 2026ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion25 May 2026
- 2026SFR-Net: Learning Scale-Frustum Representations for Ultra-Wide Area Remote Sensing Image Segmentation25 May 2026
- 2026OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization19 May 2026
- 2026Sapiens223 Apr 2026
- 2026PEPR: Privileged Event-based Predictive Regularization for Domain Generalization4 Feb 2026
- 2026Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping16 Jan 2026
- 2026WeedRepFormer: Reparameterizable Vision Transformers for Real-Time Waterhemp Segmentation and Gender Classification6 Jan 2026
- 2026Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation3 Jan 2026
- 2025Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues7 Dec 2025
12 newest of 247 All 247 (JSON)