Methods › General › Network Shrinking › NetAdapt

NetAdapt

3 papers tagged archive 2025-07-28

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

NetAdapt is a network shrinking algorithm to adapt a pretrained network to a mobile platform given a real resource budget. NetAdapt can incorporate direct metrics, such as latency and energy, into the optimization to maximize the adaptation performance based on the characteristics of the platform. By using empirical measurements, NetAdapt can be applied to any platform as long as we can measure the desired metrics, without any knowledge of the underlying implementation of the platform.

While many existing algorithms simplify networks based on the number of MACs or weights, optimizing those indirect metrics may not necessarily reduce the direct metrics, such as latency and energy consumption. To solve this problem, NetAdapt incorporates direct metrics into its adaptation algorithm. These direct metrics are evaluated using empirical measurements, so that detailed knowledge of the platform and toolchain is not required. NetAdapt automatically and progressively simplifies a pre-trained network until the resource budget is met while maximizing the accuracy.

Source: NetAdapt: Platform-Aware Neural Network Adaptation for...See Code · denru01/netadapt

Papers archive 2025-07-28

3 shown of 3, 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.

SAR ATR under Limited Training Data Via MobileNetV3
27 Jun 2023 · 1 repository · arXiv:2306.15287
Searching for MobileNetV3
6 May 2019 · 67 repositories · arXiv:1905.02244

Syntology ran 58 of 105 samples · 47 unverified · 46 pointer-only (licence)
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
9 Apr 2018 · 4 repositories · arXiv:1804.03230

Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)

Tasks archive 2025-07-28

11 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
Image Classification	2
CPU	1
Classification	1
Decoder	1
Dichotomous Image Segmentation	1
GPU	1
Neural Architecture Search	1
Object Detection	1
Segmentation	1
Semantic Segmentation	1
image-classification	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (3 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

Network Shrinking

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