Methods › General › Inference Engines › Mobile Neural Network

MNN

Mobile Neural Network

4 papers tagged archive 2025-07-28

Introduced by Xiaotang Jiang et al. in MNN: A Universal and Efficient Inference Engine

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Mobile Neural Network (MNN) is a mobile inference engine tailored to mobile applications. The contributions of MNN include: (1) presenting a mechanism called pre-inference that manages to conduct runtime optimization; (2) delivering thorough kernel optimization on operators to achieve optimal computation performance; (3) introducing backend abstraction module which enables hybrid scheduling and keeps the engine lightweight.

Paper Source

Papers archive 2025-07-28

4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices
17 Dec 2024 · 0 repositories · arXiv:2412.13273
NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement
20 Jun 2023 · 1 repository · arXiv:2306.11920
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
30 May 2022 · 0 repositories · arXiv:2205.14833
MNN: A Universal and Efficient Inference Engine
27 Feb 2020 · 1 repository · arXiv:2002.12418

Syntology ran 0 of 8 samples · 8 unverified

Tasks archive 2025-07-28

14 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Action Recognition	1
Color Manipulation	1
Deep Learning	1
Diversity	1
Image Enhancement	1
Motion Estimation	1
Object Tracking	1
Optical Flow Estimation	1
Photo Retouching	1
Scheduling	1
Tone Mapping	1
Video Generation	1
Video Restoration	1
Video Stabilization	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (4 dated). Bars are counts, not a trend claim.

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

Inference Engines

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