{"url":"/method/fcn","slug":"fcn","name":"FCN","full_name":"Fully Convolutional Network","full_name_withheld":false,"description_markdown":"**Fully Convolutional Networks**, or **FCNs**, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as [convolution](https://paperswithcode.com/method/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.\r\n\r\nThe network consists of a downsampling path, used to extract and interpret the context, and an upsampling path, which allows for localization. \r\n\r\nFCNs also employ skip connections to recover the fine-grained spatial information lost in the downsampling path.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Fully Convolutional Networks for Semantic Segmentation","paper":"/paper/fully-convolutional-networks-for-semantic","first_author":"Evan Shelhamer","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/fully-convolutional-networks-for-semantic"},"source":{"url":"http://arxiv.org/abs/1605.06211v1","title":"Fully Convolutional Networks for Semantic Segmentation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/Jackey9797/FCN","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":285,"archive_num_papers":285,"papers_newest_first":[{"paper":null,"title":"Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation","date":"2025-02-06","arxiv_id":"2502.03813","n_code_links":0,"syntology":null},{"paper":"/paper/an-end-to-end-approach-for-korean-wakeword","title":"An End-to-End Approach for Korean Wakeword Systems with Speaker Authentication","date":"2025-01-21","arxiv_id":"2501.12194","n_code_links":2,"syntology":null},{"paper":null,"title":"Geospatial Data Fusion: Combining Lidar, SAR, and Optical Imagery with AI for Enhanced Urban Mapping","date":"2024-12-25","arxiv_id":"2412.18994","n_code_links":0,"syntology":null},{"paper":null,"title":"On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks","date":"2024-12-09","arxiv_id":"2412.06545","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Fully Convolutional Networks for the Segmentation of Hyperspectral Imaging Applied to Advanced Driver Assistance Systems","date":"2024-12-05","arxiv_id":"2412.03982","n_code_links":0,"syntology":null},{"paper":null,"title":"Rapid Deployment of Domain-specific Hyperspectral Image Processors with Application to Autonomous Driving","date":"2024-11-26","arxiv_id":"2411.17543","n_code_links":0,"syntology":null},{"paper":"/paper/satvision-toa-a-geospatial-foundation-model","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","date":"2024-11-26","arxiv_id":"2411.17000","n_code_links":1,"syntology":null},{"paper":null,"title":"Multimodal 3D Brain Tumor Segmentation with Adversarial Training and Conditional Random Field","date":"2024-11-21","arxiv_id":"2411.14418","n_code_links":0,"syntology":null},{"paper":null,"title":"Self-Supervised Learning of Grasping Arbitrary Objects On-the-Move","date":"2024-11-15","arxiv_id":"2411.09904","n_code_links":0,"syntology":null},{"paper":null,"title":"An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation","date":"2024-09-14","arxiv_id":"2409.09530","n_code_links":0,"syntology":null},{"paper":"/paper/image-segmentation-in-foundation-model-era-a","title":"Image Segmentation in Foundation Model Era: A Survey","date":"2024-08-23","arxiv_id":"2408.12957","n_code_links":1,"syntology":null},{"paper":null,"title":"Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery","date":"2024-07-27","arxiv_id":"2407.19184","n_code_links":0,"syntology":null},{"paper":"/paper/dcnv3-towards-next-generation-deep-cross","title":"FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction","date":"2024-07-18","arxiv_id":"2407.13349","n_code_links":2,"syntology":null},{"paper":"/paper/make-a-strong-teacher-with-label-assistance-a","title":"Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation","date":"2024-07-18","arxiv_id":"2407.13254","n_code_links":1,"syntology":null},{"paper":null,"title":"Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot","date":"2024-06-11","arxiv_id":"2406.06893","n_code_links":0,"syntology":null},{"paper":null,"title":"Improving Prediction Accuracy of Semantic Segmentation Methods Using Convolutional Autoencoder Based Pre-processing Layers","date":"2024-04-19","arxiv_id":"2404.12718","n_code_links":0,"syntology":null},{"paper":null,"title":"Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks","date":"2024-04-05","arxiv_id":"2404.04244","n_code_links":0,"syntology":null},{"paper":"/paper/multiscale-low-frequency-memory-network-for","title":"Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks","date":"2024-03-13","arxiv_id":"2403.08157","n_code_links":1,"syntology":null},{"paper":null,"title":"High-speed Low-consumption sEMG-based Transient-state micro-Gesture Recognition","date":"2024-03-04","arxiv_id":"2403.06998","n_code_links":0,"syntology":null},{"paper":null,"title":"Graph convolutional network as a fast statistical emulator for numerical ice sheet modeling","date":"2024-02-07","arxiv_id":"2402.05291","n_code_links":0,"syntology":null},{"paper":null,"title":"Vertical Federated Image Segmentation","date":"2024-01-15","arxiv_id":"2401.07931","n_code_links":0,"syntology":null},{"paper":null,"title":"Horizontal Federated Computer Vision","date":"2023-12-31","arxiv_id":"2401.00390","n_code_links":0,"syntology":null},{"paper":"/paper/brain-inspired-visual-odometry-balancing","title":"Brain-Inspired Visual Odometry: Balancing Speed and Interpretability through a System of Systems Approach","date":"2023-12-20","arxiv_id":"2312.13162","n_code_links":1,"syntology":null},{"paper":null,"title":"AttenScribble: Attentive Similarity Learning for Scribble-Supervised Medical Image Segmentation","date":"2023-12-11","arxiv_id":"2312.06614","n_code_links":0,"syntology":null},{"paper":"/paper/maskconver-revisiting-pure-convolution-model","title":"MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation","date":"2023-12-11","arxiv_id":"2312.06052","n_code_links":1,"syntology":null},{"paper":null,"title":"Tool Wear Segmentation in Blanking Processes with Fully Convolutional Networks based Digital Image Processing","date":"2023-10-06","arxiv_id":"2311.12841","n_code_links":0,"syntology":null},{"paper":null,"title":"Diagnosis of Scalp Disorders using Machine Learning and Deep Learning Approach -- A Review","date":"2023-08-14","arxiv_id":"2308.07052","n_code_links":0,"syntology":null},{"paper":"/paper/image-segmentation-keras-implementation-of","title":"Image Segmentation Keras : Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras","date":"2023-07-25","arxiv_id":"2307.13215","n_code_links":2,"syntology":null},{"paper":null,"title":"Object-based Probabilistic Similarity Evidence of Sparse Latent Features from Fully Convolutional Networks","date":"2023-07-25","arxiv_id":"2307.13606","n_code_links":0,"syntology":null},{"paper":null,"title":"Patch-CNN: Training data-efficient deep learning for high-fidelity diffusion tensor estimation from minimal diffusion protocols","date":"2023-07-03","arxiv_id":"2307.01346","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":112},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":101},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":44},{"task":"/task/object-detection","name":"Object Detection","papers":24},{"task":"/task/object-detection-1","name":"object-detection","papers":22},{"task":"/task/classification","name":"General Classification","papers":20},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":20},{"task":"/task/decoder","name":"Decoder","papers":18},{"task":"/task/image-classification","name":"Image Classification","papers":15},{"task":"/task/object","name":"Object","papers":13},{"task":"/task/image-classification","name":"image-classification","papers":13},{"task":"/task/classification-1","name":"Classification","papers":9},{"task":"/task/time-series-1","name":"Time Series","papers":9},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":9},{"task":"/task/medical-image-analysis","name":"Medical Image Analysis","papers":8},{"task":"/task/tumor-segmentation","name":"Tumor Segmentation","papers":8},{"task":"/task/regression-1","name":"regression","papers":8},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":7},{"task":"/task/deep-learning","name":"Deep Learning","papers":7},{"task":"/task/denoising","name":"Denoising","papers":7}],"tasks_shown":20,"n_tasks":236,"usage_by_year":[{"year":"2015","papers":1},{"year":"2016","papers":22},{"year":"2017","papers":36},{"year":"2018","papers":41},{"year":"2019","papers":49},{"year":"2020","papers":42},{"year":"2021","papers":26},{"year":"2022","papers":26},{"year":"2023","papers":21},{"year":"2024","papers":19},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/fcn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}