Papers › Searching for MobileNetV3
Searching for MobileNetV3
Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam
We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone CPUs through a combination of hardware-aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances. This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art. Through this process we create two new MobileNet models for release: MobileNetV3-Large and MobileNetV3-Small which are targeted for high and low resource use cases. These models are then adapted and applied to the tasks of object detection and semantic segmentation. For the task of semantic segmentation (or any dense pixel prediction), we propose a new efficient segmentation decoder Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP). We achieve new state of the art results for mobile classification, detection and segmentation. MobileNetV3-Large is 3.2\% more accurate on ImageNet classification while reducing latency by 15\% compared to MobileNetV2. MobileNetV3-Small is 4.6\% more accurate while reducing latency by 5\% compared to MobileNetV2. MobileNetV3-Large detection is 25\% faster at roughly the same accuracy as MobileNetV2 on COCO detection. MobileNetV3-Large LR-ASPP is 30\% faster than MobileNetV2 R-ASPP at similar accuracy for Cityscapes segmentation.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1905.02244")
Code
Syntology Ran 58 of 105 code samples harvested from 22 repositories linked to this paper; 47 have no recorded run. Of those that ran: 6 ran · honoured contract; 2 ran · violated contract; 7 ran · our draft was wrong; 4 ran · fixture could not drive it; 39 ran with no contract checked.
By repository: community (archive-listed): 105 samples from 22 repositories, 58 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
67 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
105 samples harvested; 58 ran; 6 honoured the contract we drafted; 47 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
Licence: 46 of the 105 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 22 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
9a228be8d95a8267 · report
9e476824ce6c9115 · report
379eb0ad4b8f3ec3 · report
eea0d2df8bb7cbe4 · report
d44d7e19fe65cbc2 · report
fae9673025e2a220 · report
557fa0210dc2d24b · report
0d8cfba511f31324 · report
fda5ccaf76461ba5 · report
0ae7cf2c14285d34 · report
4a269a6484171c4e · report
d276d941f05c6062 · report
9942e2eaf6ad275b · report
708f8102eea91f9e · report
3b87793a966b3e95 · report
ace014323d335247 · report
e1bd359a8a7b96b2 · report
8725aa67394a59c0 · report
9e8d7789c4c389a6 · report
2d8a3aa3bbd7b78a · report
7f869bd47b2a9653 · report
dd0eb9bdaecad128 · report
f54f64d3a22943e8 · report
a0eb27e3a8ffc484 · report
6278668ba6ef59f3 · report
0c9f35bd6df82dc7 · report
2d9873a3665e1dd9 · report
3a744d625048086e · report
c89b0dcd2fc64746 · report
be1d6e0d4c7fbed8 · report
518da7f7fc849e72 · report
544e406c29c4e4cb · report
3ba84df153cca41e · report
06ed09c8c4a05763 · report
03eee59192d9c54e · report
ce856d9e51a3df05 · report
d04dc47c293a9646 · report
6a0317bfd6be9557 · report
6e59364a7cf6008f · report
704704cc698dd1a4 · report
4e90491a30c2dc28 · report
db82a4013a44fb42 · report
5221887077e3fb54 · report
84a4cf301e929085 · report
927b92925cff89c3 · report
47cebc13301c1e23 · report
74b185a45e459a10 · report
a9a67906bc9afd8a · report
da02b7e3f57b5d87 · report
7bcd0f441e3a0c6f · report
ad3e66a9d6a27e29 · report
ecb1dac2f3a2944a · report
9f9ace2e0eb7c4fe · report
63ec083689f80f47 · report
5426806a2db402eb · report
02cff13546af958b · report
91abe93c3f37f65f · report
bc3a3914c7eee220 · report
d0eb453f4721591c · report
bb95cb930e46eee0 · report
561f7b0eb338927a · report
ddd66ea3aa2a3a65 · report
271746eae93de918 · report
5733827ea6ca2df0 · report
5d99159796ececdc · report
b82827563bc7975b · report
a27dd3605bd35022 · report
ecdc06194e69eea3 · report
2049f6182035adfb · report
812a03560e02d125 · report
5528da7e34b0c499 · report
fd81c5c2c0790a12 · report
4ec99f9f08732346 · report
b700fb0a3496b255 · report
d97a5cf595717b21 · report
bc162101f2b2253f · report
d842549186ebc802 · report
24e984c89fc9c4d5 · report
4f22ad4d050b6b59 · report
d55431cb0ee73cd8 · report
4e6344480f924830 · report
4d72a8990678d08d · report
f1abace867b0c498 · report
04e390b8fa4ddf5b · report
bcab367eb4c6388e · report
199223de2f9704cf · report
a5c3c9ce1a8998c4 · report
0ef0019514eaaa09 · report
ed8b51c771d7b05f · report
ad6446d870a72a89 · report
eed594a74863387a · report
df8e996291f19181 · report
4cbeebb0d2fd1171 · report
f630f3f49e01f56f · report
f196628d978e9c99 · report
453e3b4fdec6b005 · report
1cbae9505b4428d7 · report
059dddf26b4004e7 · report
a3f3322fd8b895ef · report
44867397fdc5b044 · report
7468ea92c204fba0 · report
424f887a9c6c2078 · report
67137622a1231779 · report
5344df98353e9f50 · report
944db263a2d0cf75 · report
Tasks
Results from the paper archive 2025-07-28
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: Hard Swish
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