Description
The ENet Initial Block is an image model block used in the ENet semantic segmentation architecture. Max Pooling is performed with non-overlapping 2 × 2 windows, and the convolution has 13 filters, which sums up to 16 feature maps after concatenation. This is heavily inspired by Inception Modules.
Papers Using This Method
Early Explorations of Lightweight Models for Wound Segmentation on Mobile Devices2024-07-10DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction2023-12-01Resource Constrained Semantic Segmentation for Waste Sorting2023-10-30Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml2022-05-16Efficient Accelerator for Dilated and Transposed Convolution with Decomposition2022-05-02Improving evidential deep learning via multi-task learning2021-12-17Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?2021-07-23MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring2020-12-05Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training2020-10-21Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving2020-08-11Deep Learning-based Aerial Image Segmentation with Open Data for Disaster Impact Assessment2020-06-10Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices2019-09-15Learning Lightweight Lane Detection CNNs by Self Attention Distillation2019-08-02DENet: A Universal Network for Counting Crowd with Varying Densities and Scales2019-04-17Real time backbone for semantic segmentation2019-03-16DSNet for Real-Time Driving Scene Semantic Segmentation2018-12-06Efficient Semantic Segmentation for Visual Bird's-eye View Interpretation2018-11-29SNAP: A semismooth Newton algorithm for pathwise optimization with optimal local convergence rate and oracle properties2018-10-09A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation2018-07-16Mapping Road Lanes Using Laser Remission and Deep Neural Networks2018-04-27