TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/FCN

FCN

Fully Convolutional Network

Computer VisionIntroduced 2000285 papers
Source Paper

Description

Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as convolution, pooling and upsampling. Avoiding the use of dense layers means less parameters (making the networks faster to train). It also means an FCN can work for variable image sizes given all connections are local.

The network consists of a downsampling path, used to extract and interpret the context, and an upsampling path, which allows for localization.

FCNs also employ skip connections to recover the fine-grained spatial information lost in the downsampling path.

Papers Using This Method

Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation2025-02-06An End-to-End Approach for Korean Wakeword Systems with Speaker Authentication2025-01-21Geospatial Data Fusion: Combining Lidar, SAR, and Optical Imagery with AI for Enhanced Urban Mapping2024-12-25On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks2024-12-09Exploring Fully Convolutional Networks for the Segmentation of Hyperspectral Imaging Applied to Advanced Driver Assistance Systems2024-12-05Rapid Deployment of Domain-specific Hyperspectral Image Processors with Application to Autonomous Driving2024-11-26SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery2024-11-26Multimodal 3D Brain Tumor Segmentation with Adversarial Training and Conditional Random Field2024-11-21Self-Supervised Learning of Grasping Arbitrary Objects On-the-Move2024-11-15An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation2024-09-14Image Segmentation in Foundation Model Era: A Survey2024-08-23Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery2024-07-27Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation2024-07-18FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction2024-07-18Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot2024-06-11Improving Prediction Accuracy of Semantic Segmentation Methods Using Convolutional Autoencoder Based Pre-processing Layers2024-04-19Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks2024-04-05Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks2024-03-13High-speed Low-consumption sEMG-based Transient-state micro-Gesture Recognition2024-03-04Graph convolutional network as a fast statistical emulator for numerical ice sheet modeling2024-02-07