Papers › Dynamic Routing Between Capsules
Dynamic Routing Between Capsules
Sara Sabour, Nicholas Frosst, Geoffrey E. Hinton
A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters. Active capsules at one level make predictions, via transformation matrices, for the instantiation parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active. We show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits. To achieve these results we use an iterative routing-by-agreement mechanism: A lower-level capsule prefers to send its output to higher level capsules whose activity vectors have a big scalar product with the prediction coming from the lower-level capsule.
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="1710.09829")
Code
Syntology Ran 18 of 118 code samples harvested from 35 repositories linked to this paper; 100 have no recorded run. Of those that ran: 15 ran · our draft was wrong; 2 ran · fixture could not drive it; 1 ran with no contract checked.
By repository: official repository: 2 samples from 1 repository, 0 ran; community (archive-listed): 115 samples from 34 repositories, 17 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
77 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
118 samples harvested; 18 ran; 0 honoured the contract we drafted; 100 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: 12 of the 118 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 35 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.
9752e0af7e2e920e · report
b1b870e26b8c5598 · report
64858477ea4e51d9 · report
916d6f93349e426b · report
c0f267f39366e309 · report
6d94bff65a753b0d · report
9169bb6c16583f82 · report
b72eda3284443993 · report
e161978d5621fd5a · report
fa45f6e21e1f5d6e · report
19f6c412420d3c16 · report
c4647dd5ef46a3fd · report
c5a569bffcb9d305 · report
d55eaf6b69be6376 · report
43a28458e2019a51 · report
ac7650b0121cd6c9 · report
36782ecd204f05d4 · report
89d981e0b618190e · report
5abcd8c6705f2368 · report
643e4ac03170a791 · report
313487a9c6ca5c62 · report
c52aed0e8829960c · report
1fcca424e3c93303 · report
2329d95d55ec1505 · report
6c522a777d335f98 · report
0d412a9be3a2a5d6 · report
25474dc6ec455a0d · report
2e8edc862c5c964a · report
ef26365c2b293ba7 · report
ae560fa01740cfe8 · report
f47fb66b0f1495bb · report
958171517f243d79 · report
e681684c378bcb1e · report
a4f9b362c3fb2a02 · report
889c715d11d8841d · report
04b01a6b962167f2 · report
579b9526c3924ec3 · report
b212ca24ab843e8a · report
ba9a20e6fac96f58 · report
3e0f4a3cdf8f7d0e · report
fe870e6febcb38d2 · report
512bf4bce2286e2e · report
aeb7fd30067180af · report
1e8dccecc001d2fd · report
9e374d498da47a80 · report
5c5b8a89cd91d2f6 · report
4d42218ea782618b · report
89675961d6c5df8a · report
d266f1b82443c200 · report
22def68ffad5b584 · report
8cc74d9d9716f3e5 · report
354cb4ef853ea7c0 · report
e9572b0ab2492828 · report
0fa7ba2d6f1b5e7d · report
9ef54be9d13fc447 · report
a4fd5ddd12015349 · report
cd1f1b152fc81869 · report
9609ff43029770e8 · report
928c0a98317f2f9c · report
2ecfcd586e6b8acf · report
9e266efd2f9b3537 · report
d805a7b2c2d7d3ad · report
78eab6842a55500d · report
25c21be9120353e4 · report
18f1ac5a3bb1245f · report
4293fbb258948def · report
ef6f7f989e63e349 · report
3619549fb958505d · report
5c2f7dad1037f39e · report
4b0f312bd2a3e344 · report
bebfab67566d4deb · report
c23def11ceb6917f · report
c2c66bc5a1670838 · report
7b208df6adf33efe · report
954a41787b10fdf8 · report
f7af01a437e72215 · report
454894a6d26864c2 · report
a6d3be25cfdf1fe4 · report
906e695c111ae448 · report
a60140719ee8eeab · report
f57a3bb8459d9735 · report
93341244192ac2a3 · report
45ba4b2229e7c5d0 · report
c5ff48b72a93fec5 · report
8278b9f74e0d99c0 · report
71f308af9ead46b8 · report
60b0489fcce178c8 · report
7e43778f815ea3c2 · report
d47f898b34da72b5 · report
ad88fd8ea70fc685 · report
59858e235d46459f · report
7f6b9d28c90431fb · report
7b42b0ac5492beb9 · report
df095bccc89495e4 · report
0da33f8508f5c3ef · report
c95802bf73f69647 · report
23664ef48d2b7fc9 · report
f62923a58d77cb1c · report
09124db7cc72c4f5 · report
852e571b48325d2a · report
904b93c8951de375 · report
94a9d3fa58aca150 · report
2719723f2846d85e · report
fed6154c45168494 · report
bc53226908b5d193 · report
42ce6a693b03e2f2 · report
e6c4c09caf295822 · report
d1e743564e5d4d8c · report
5568e495aa546957 · report
f854823338dc9ee8 · report
9baf4429c73eff71 · report
a5be0ded65ff286c · report
bf56a8a6277e51bd · report
6c016f20008ba616 · report
5e53f8244d86e2f9 · report
0ab110223d3720af · report
09b60348edfeca3d · report
e8e375ca46107111 · report
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | CIFAR-10 | ensemble of 7 models | Percentage correct | 89.4 | #209 of 265 | Archive leaderboard | report |
| Image Classification | EMNIST-Balanced | TextCaps | Accuracy | 90.46 | #6 of 20 | Archive leaderboard | report |
| Image Classification | MNIST | CapsNet | Percentage error | 0.25 | #12 of 81 | Archive leaderboard | report |
| Image Classification | MultiMNIST | CapsNet | Percentage error | 5.2 | #1 of 1 | Archive leaderboard | report |
| Image Classification | smallNORB | CapsNet | Classification Error | 3.77 | #6 of 7 | Archive leaderboard | report |
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: CapsNet, Capsule Network
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