Methods › Computer Vision › Convolutional Neural Networks › MnasNet
MnasNet
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
MnasNet is a type of convolutional neural network optimized for mobile devices that is discovered through mobile neural architecture search, which explicitly incorporates model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. The main building block is an inverted residual block (from MobileNetV2).
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1807.11626'). Repositories: 29 listed of 29 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:1807.11626, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1807.11626) is about this method is not checked.
Origin paper of this answer, arXiv:1807.11626 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 6 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: 20 · with a code link: 12 · where Syntology ran a sample: 3 (3 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 (3 of 20 tagged: 3 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 20 of 20, 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.
-
The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features 26 Jul 2023 · 1 repository · arXiv:2307.13953
-
SAR ATR under Limited Training Data Via MobileNetV3 27 Jun 2023 · 1 repository · arXiv:2306.15287
-
Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance 26 Nov 2022 · 0 repositories · arXiv:2211.14487
-
An embarrassingly simple comparison of machine learning algorithms for indoor scene classification 25 Sep 2021 · 1 repository · arXiv:2109.12261
-
HAO: Hardware-aware neural Architecture Optimization for Efficient Inference 26 Apr 2021 · 0 repositories · arXiv:2104.12766
-
Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation 19 Apr 2021 · 0 repositories · arXiv:2104.09648
-
Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces 16 Dec 2020 · 0 repositories · arXiv:2012.08859
-
Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs 6 Nov 2020 · 1 repository · arXiv:2011.04475
-
R-MnasNet: Reduced MnasNet for Computer Vision 8 Oct 2020 · 0 repositories
-
EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search 16 Sep 2020 · 3 repositories · arXiv:2009.07409
-
Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers 12 Aug 2020 · 0 repositories · arXiv:2008.05124
-
To Filter Prune, or to Layer Prune, That Is The Question 11 Jul 2020 · 1 repository · arXiv:2007.05667
-
Fine-Grained Stochastic Architecture Search 17 Jun 2020 · 1 repository · arXiv:2006.09581Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices 7 May 2020 · 0 repositories · arXiv:2005.05085
-
Neural Epitome Search for Architecture-Agnostic Network Compression 12 Jul 2019 · 0 repositories · arXiv:1907.05642
-
Attention Augmented Convolutional Networks 22 Apr 2019 · 14 repositories · arXiv:1904.09925Syntology 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
CondConv: Conditionally Parameterized Convolutions for Efficient Inference 10 Apr 2019 · 9 repositories · arXiv:1904.04971
-
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers 27 Mar 2019 · 10 repositories · arXiv:1903.11728
-
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation 21 Dec 2018 · 1 repository · arXiv:1812.08934
-
MnasNet: Platform-Aware Neural Architecture Search for Mobile 31 Jul 2018 · 29 repositories · arXiv:1807.11626Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 28 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