{"url":"/method/enet","slug":"enet","name":"ENet","full_name":"ENet","full_name_withheld":false,"description_markdown":"**ENet** is a semantic segmentation architecture which utilises a compact encoder-decoder architecture. Some design choices include:\r\n\r\n1. Using the [SegNet](https://paperswithcode.com/method/segnet) approach to downsampling y saving indices of elements chosen in max\r\npooling layers, and using them to produce sparse upsampled maps in the decoder.\r\n2.  Early downsampling to optimize the early stages of the network and reduce the cost of processing large input frames. The first two blocks of ENet heavily reduce the input size, and use only a small set of feature maps. \r\n3. Using PReLUs as an activation function\r\n4. Using dilated convolutions \r\n5. Using Spatial [Dropout](https://paperswithcode.com/method/dropout)","description_state":"present","introduced_year":null,"introduced_by":{"title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","paper":"/paper/enet-a-deep-neural-network-architecture-for","first_author":"Adam Paszke","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/enet-a-deep-neural-network-architecture-for"},"source":{"url":"http://arxiv.org/abs/1606.02147v1","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/iArunava/ENet-Real-Time-Semantic-Segmentation/blob/8a09a709f46544b229b37654c57ce5ae512fd398/models/ENet.py#L24","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":24,"archive_num_papers":24,"papers_newest_first":[{"paper":null,"title":"Early Explorations of Lightweight Models for Wound Segmentation on Mobile Devices","date":"2024-07-10","arxiv_id":"2407.07605","n_code_links":0,"syntology":null},{"paper":"/paper/docreal-robust-document-dewarping-of-real","title":"DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction","date":"2023-12-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":"/paper/resource-constrained-semantic-segmentation","title":"Resource Constrained Semantic Segmentation for Waste Sorting","date":"2023-10-30","arxiv_id":"2310.19407","n_code_links":1,"syntology":null},{"paper":null,"title":"Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml","date":"2022-05-16","arxiv_id":"2205.07690","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Accelerator for Dilated and Transposed Convolution with Decomposition","date":"2022-05-02","arxiv_id":"2205.02103","n_code_links":0,"syntology":null},{"paper":"/paper/improving-evidential-deep-learning-via-multi","title":"Improving evidential deep learning via multi-task learning","date":"2021-12-17","arxiv_id":"2112.09368","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?","date":"2021-07-23","arxiv_id":"2107.11447","n_code_links":0,"syntology":null},{"paper":"/paper/myfood-a-food-segmentation-and-classification","title":"MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring","date":"2020-12-05","arxiv_id":"2012.03087","n_code_links":0,"syntology":null},{"paper":null,"title":"Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training","date":"2020-10-21","arxiv_id":"2010.12440","n_code_links":0,"syntology":null},{"paper":null,"title":"Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving","date":"2020-08-11","arxiv_id":"2008.04751","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Learning-based Aerial Image Segmentation with Open Data for Disaster Impact Assessment","date":"2020-06-10","arxiv_id":"2006.05575","n_code_links":0,"syntology":null},{"paper":null,"title":"Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices","date":"2019-09-15","arxiv_id":"1909.06840","n_code_links":0,"syntology":null},{"paper":"/paper/learning-lightweight-lane-detection-cnns-by","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","date":"2019-08-02","arxiv_id":"1908.00821","n_code_links":2,"syntology":{"ran":2,"of":8,"unverified":6,"pointer_only":0}},{"paper":null,"title":"DENet: A Universal Network for Counting Crowd with Varying Densities and Scales","date":"2019-04-17","arxiv_id":"1904.08056","n_code_links":0,"syntology":null},{"paper":null,"title":"Real time backbone for semantic segmentation","date":"2019-03-16","arxiv_id":"1903.06922","n_code_links":0,"syntology":null},{"paper":null,"title":"DSNet for Real-Time Driving Scene Semantic Segmentation","date":"2018-12-06","arxiv_id":"1812.07049","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Semantic Segmentation for Visual Bird's-eye View Interpretation","date":"2018-11-29","arxiv_id":"1811.12008","n_code_links":0,"syntology":null},{"paper":null,"title":"SNAP: A semismooth Newton algorithm for pathwise optimization with optimal local convergence rate and oracle properties","date":"2018-10-09","arxiv_id":"1810.03814","n_code_links":0,"syntology":null},{"paper":"/paper/a-dataset-of-laryngeal-endoscopic-images-with","title":"A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation","date":"2018-07-16","arxiv_id":"1807.06081","n_code_links":1,"syntology":null},{"paper":null,"title":"Mapping Road Lanes Using Laser Remission and Deep Neural Networks","date":"2018-04-27","arxiv_id":"1804.10662","n_code_links":0,"syntology":null},{"paper":null,"title":"Computationally efficient cardiac views projection using 3D Convolutional Neural Networks","date":"2017-11-03","arxiv_id":"1711.01345","n_code_links":0,"syntology":null},{"paper":"/paper/fast-scene-understanding-for-autonomous","title":"Fast Scene Understanding for Autonomous Driving","date":"2017-08-08","arxiv_id":"1708.02550","n_code_links":1,"syntology":null},{"paper":null,"title":"FastVentricle: Cardiac Segmentation with ENet","date":"2017-04-13","arxiv_id":"1704.04296","n_code_links":0,"syntology":null},{"paper":"/paper/enet-a-deep-neural-network-architecture-for","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","date":"2016-06-07","arxiv_id":"1606.02147","n_code_links":49,"syntology":{"ran":5,"of":30,"unverified":25,"pointer_only":0}}],"papers_shown":24,"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":13},{"task":"/task/segmentation","name":"Segmentation","papers":10},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":5},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":2},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/deep-learning","name":"Deep Learning","papers":2},{"task":"/task/efficient-neural-network","name":"Efficient Neural Network","papers":2},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":2},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/medical-image-analysis","name":"Medical Image Analysis","papers":2},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","papers":2},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":2},{"task":"/task/regression-1","name":"regression","papers":2},{"task":"/task/cardiac-segmentation","name":"Cardiac Segmentation","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/disaster-response","name":"Disaster Response","papers":1}],"tasks_shown":20,"n_tasks":38,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":3},{"year":"2018","papers":5},{"year":"2019","papers":4},{"year":"2020","papers":4},{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2024","papers":1}],"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/enet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}