Learnable box filters and precomputed summed-area tables enable efficient arbitrarily large kernel convolutions in fully-convolutional networks while maintaining constant parameters per filter and competitive performance on human pose estimation.
hub
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
abstract
The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point operations and have long run-times that hinder their usability. In this paper, we propose a novel deep neural network architecture named ENet (efficient neural network), created specifically for tasks requiring low latency operation. ENet is up to 18$\times$ faster, requires 75$\times$ less FLOPs, has 79$\times$ less parameters, and provides similar or better accuracy to existing models. We have tested it on CamVid, Cityscapes and SUN datasets and report on comparisons with existing state-of-the-art methods, and the trade-offs between accuracy and processing time of a network. We present performance measurements of the proposed architecture on embedded systems and suggest possible software improvements that could make ENet even faster.
hub tools
citation-role summary
method 2
citation-polarity summary
verdicts
UNVERDICTED 20roles
method 2polarities
use method 2representative citing papers
Patch-wise sparse MoE layers in CNNs for semantic segmentation yield architecture-dependent gains up to 3.9 mIoU on Cityscapes and BDD100K with low overhead, but show strong design sensitivity.
GABI augments a convolutional backbone with an auxiliary distance-field prediction head to improve spacecraft segmentation accuracy and generalization under variable illumination while remaining lightweight.
PILOT adds a parallel D-branch to PIDNet for boundary-guided incremental learning of new semantic classes using only new data while preserving base class performance.
RED is a deadline-aware DAG scheduler for robotic multi-task inference that adapts to environmental dynamics and supports MIMONet deployment.
BCAF fuses native-resolution RGB and low-resolution hyperspectral inputs via bidirectional localized cross-attention and reports 75.4% on SpectralWaste plus 62–66% mIoU on a new industrial recycling dataset at real-time rates.
Attention-Mamba uses parallel branches, Recursive Alignment Module, and Mamba-enhanced attention to report highest segmentation accuracy on Synapse, ACDC, ISIC-2018, and PH2 with 14.05M parameters and 8.94 GFLOPs.
Combines pre-trained features, Bayesian regression, and moment propagation to enable real-time epistemic uncertainty for semantic segmentation on embedded systems while preserving accuracy.
A lightweight segmentation network learns associative embeddings to assign consistent descriptors to unconnected pixels of same-team players for game-agnostic team discrimination in basketball videos.
A pipeline uses Mask2Former flood masks and DEMs to compute a single water surface elevation then derives local depths under hydrostatic equilibrium.
A survey organizes synthetic data use, digital twin simulation, and domain adaptation techniques for autonomous driving while identifying open challenges like Sim2Real transfer.
TwinLiteNet+ is a hybrid-encoder multi-task segmentation model with new UCB, USB, and PCAA modules that reports 92.9% mIoU on drivable area and 34.2% IoU on lane segmentation on BDD100K while using 11x fewer FLOPs than prior models.
Adapts SwiftNet into SFN with ERFNet/GCNet-inspired blocks and compares loss functions, classifiers, and decision rules to increase recall in real-time semantic segmentation on CamVid and Cityscapes.
ESNet is a lightweight symmetric CNN using factorized residual units and parallel dilated convolutions that reaches over 62 FPS semantic segmentation on Cityscapes with 1.6M parameters.
DA-SegFormer reaches 74.61% mIoU on RescueNet by adding class-aware sampling and OHEM-Dice loss to SegFormer, delivering double-digit gains on minor and major damage classes.
FoR-Net improves efficiency in semantic segmentation by focusing on hard regions with a learned selector and multi-scale convolutions, achieving competitive results on Cityscapes.
Introduces importance-aware loss and BiERF-PSPNet extension for semantic segmentation tailored to navigational assistant systems, evaluated on CamVid and Cityscapes.
A comparison of FCNN architectures for monocular depth estimation yields a model suitable for real-time operation on NVidia Jetson hardware with evaluation in vSLAM.
A survey of state-of-the-art CNN architectures for agricultural IoT applications that proposes a tailored classification taxonomy and reviews existing research to guide architecture selection.
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
citing papers explorer
-
Accelerating Large-Kernel Convolution Using Summed-Area Tables
Learnable box filters and precomputed summed-area tables enable efficient arbitrarily large kernel convolutions in fully-convolutional networks while maintaining constant parameters per filter and competitive performance on human pose estimation.
-
Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
Patch-wise sparse MoE layers in CNNs for semantic segmentation yield architecture-dependent gains up to 3.9 mIoU on Cityscapes and BDD100K with low overhead, but show strong design sensitivity.
-
GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation
GABI augments a convolutional backbone with an auxiliary distance-field prediction head to improve spacecraft segmentation accuracy and generalization under variable illumination while remaining lightweight.
-
PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance
PILOT adds a parallel D-branch to PIDNet for boundary-guided incremental learning of new semantic classes using only new data while preserving base class performance.
-
RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics
RED is a deadline-aware DAG scheduler for robotic multi-task inference that adapts to environmental dynamics and supports MIMONet deployment.
-
Bidirectional Cross-Attention Fusion of High-Resolution RGB and Low-Resolution Hyperspectral Inputs for Multimodal Semantic Segmentation
BCAF fuses native-resolution RGB and low-resolution hyperspectral inputs via bidirectional localized cross-attention and reports 75.4% on SpectralWaste plus 62–66% mIoU on a new industrial recycling dataset at real-time rates.
-
Attention-Mamba: A Mamba-Enhanced Multi-Scale Parallel Inference Network for Medical Image Segmentation
Attention-Mamba uses parallel branches, Recursive Alignment Module, and Mamba-enhanced attention to report highest segmentation accuracy on Synapse, ACDC, ISIC-2018, and PH2 with 14.05M parameters and 8.94 GFLOPs.
-
Uncertainty in Real-Time Semantic Segmentation on Embedded Systems
Combines pre-trained features, Bayesian regression, and moment propagation to enable real-time epistemic uncertainty for semantic segmentation on embedded systems while preserving accuracy.
-
Associative Embedding for Game-Agnostic Team Discrimination
A lightweight segmentation network learns associative embeddings to assign consistent descriptors to unconnected pixels of same-team players for game-agnostic team discrimination in basketball videos.
-
Geometric Flood Depth Estimation: Fusing Transformer-Based Segmentation with Digital Elevation Models
A pipeline uses Mask2Former flood masks and DEMs to compute a single water surface elevation then derives local depths under hydrostatic equilibrium.
-
From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving
A survey organizes synthetic data use, digital twin simulation, and domain adaptation techniques for autonomous driving while identifying open challenges like Sim2Real transfer.
-
TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving
TwinLiteNet+ is a hybrid-encoder multi-task segmentation model with new UCB, USB, and PCAA modules that reports 92.9% mIoU on drivable area and 34.2% IoU on lane segmentation on BDD100K while using 11x fewer FLOPs than prior models.
-
A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network
Adapts SwiftNet into SFN with ERFNet/GCNet-inspired blocks and compares loss functions, classifiers, and decision rules to increase recall in real-time semantic segmentation on CamVid and Cityscapes.
-
ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
ESNet is a lightweight symmetric CNN using factorized residual units and parallel dilated convolutions that reaches over 62 FPS semantic segmentation on Cityscapes with 1.6M parameters.
-
DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment
DA-SegFormer reaches 74.61% mIoU on RescueNet by adding class-aware sampling and OHEM-Dice loss to SegFormer, delivering double-digit gains on minor and major damage classes.
-
FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation
FoR-Net improves efficiency in semantic segmentation by focusing on hard regions with a learned selector and multi-scale convolutions, achieving competitive results on Cityscapes.
-
Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems
Introduces importance-aware loss and BiERF-PSPNet extension for semantic segmentation tailored to navigational assistant systems, evaluated on CamVid and Cityscapes.
-
Real-time Vision-based Depth Reconstruction with NVidia Jetson
A comparison of FCNN architectures for monocular depth estimation yields a model suitable for real-time operation on NVidia Jetson hardware with evaluation in vSLAM.
-
Modern CNNs for IoT Based Farms
A survey of state-of-the-art CNN architectures for agricultural IoT applications that proposes a tailored classification taxonomy and reviews existing research to guide architecture selection.
-
Understanding Deep Learning Techniques for Image Segmentation
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.