Methods › Computer Vision › Semantic Segmentation Models › ENet
ENet
Introduced by Adam Paszke et al. in ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ENet is a semantic segmentation architecture which utilises a compact encoder-decoder architecture. Some design choices include:
- Using the SegNet approach to downsampling y saving indices of elements chosen in max pooling layers, and using them to produce sparse upsampled maps in the decoder.
- 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.
- Using PReLUs as an activation function
- Using dilated convolutions
- Using Spatial Dropout
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1606.02147'). Repositories: 49 listed of 49 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1606.02147, not a method entry. This answer is about arXiv:1606.02147, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1606.02147 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 26 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 30 harvested samples) · 2 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 24 · with a code link: 7 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 24 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 24 of 24, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Early Explorations of Lightweight Models for Wound Segmentation on Mobile Devices 10 Jul 2024 · 0 repositories · arXiv:2407.07605
-
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction 1 Dec 2023 · 3 repositories
-
Resource Constrained Semantic Segmentation for Waste Sorting 30 Oct 2023 · 1 repository · arXiv:2310.19407
-
Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml 16 May 2022 · 0 repositories · arXiv:2205.07690
-
Efficient Accelerator for Dilated and Transposed Convolution with Decomposition 2 May 2022 · 0 repositories · arXiv:2205.02103
-
Improving evidential deep learning via multi-task learning 17 Dec 2021 · 1 repository · arXiv:2112.09368
-
Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts? 23 Jul 2021 · 0 repositories · arXiv:2107.11447
-
MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring 5 Dec 2020 · 0 repositories · arXiv:2012.03087
-
Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training 21 Oct 2020 · 0 repositories · arXiv:2010.12440
-
Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving 11 Aug 2020 · 0 repositories · arXiv:2008.04751
-
Deep Learning-based Aerial Image Segmentation with Open Data for Disaster Impact Assessment 10 Jun 2020 · 0 repositories · arXiv:2006.05575
-
Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices 15 Sep 2019 · 0 repositories · arXiv:1909.06840
-
Learning Lightweight Lane Detection CNNs by Self Attention Distillation 2 Aug 2019 · 2 repositories · arXiv:1908.00821Syntology official (archive's flag): 1 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 1 pointer-only (licence)
-
DENet: A Universal Network for Counting Crowd with Varying Densities and Scales 17 Apr 2019 · 0 repositories · arXiv:1904.08056
-
Real time backbone for semantic segmentation 16 Mar 2019 · 0 repositories · arXiv:1903.06922
-
DSNet for Real-Time Driving Scene Semantic Segmentation 6 Dec 2018 · 0 repositories · arXiv:1812.07049
-
Efficient Semantic Segmentation for Visual Bird's-eye View Interpretation 29 Nov 2018 · 0 repositories · arXiv:1811.12008
-
SNAP: A semismooth Newton algorithm for pathwise optimization with optimal local convergence rate and oracle properties 9 Oct 2018 · 0 repositories · arXiv:1810.03814
-
A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation 16 Jul 2018 · 1 repository · arXiv:1807.06081
-
Mapping Road Lanes Using Laser Remission and Deep Neural Networks 27 Apr 2018 · 0 repositories · arXiv:1804.10662
-
Computationally efficient cardiac views projection using 3D Convolutional Neural Networks 3 Nov 2017 · 0 repositories · arXiv:1711.01345
-
Fast Scene Understanding for Autonomous Driving 8 Aug 2017 · 1 repository · arXiv:1708.02550
-
FastVentricle: Cardiac Segmentation with ENet 13 Apr 2017 · 0 repositories · arXiv:1704.04296
-
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation 7 Jun 2016 · 49 repositories · arXiv:1606.02147Syntology 26 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 30 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 38 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections