Papers › Stacked Capsule Autoencoders

Stacked Capsule Autoencoders

17 Jun 2019NeurIPS 2019 12arXiv:1906.06818archive 2025-07-28

Adam R. Kosiorek, Sara Sabour, Yee Whye Teh, Geoffrey E. Hinton

Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not depend on the viewpoint, our model is robust to viewpoint changes. SCAE consists of two stages. In the first stage, the model predicts presences and poses of part templates directly from the image and tries to reconstruct the image by appropriately arranging the templates. In the second stage, SCAE predicts parameters of a few object capsules, which are then used to reconstruct part poses. Inference in this model is amortized and performed by off-the-shelf neural encoders, unlike in previous capsule networks. We find that object capsule presences are highly informative of the object class, which leads to state-of-the-art results for unsupervised classification on SVHN (55%) and MNIST (98.7%). The code is available at https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 29 code samples harvested from 4 repositories linked to this paper: 25 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 1 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 22 samples from 3 repositories, 22 ran (21 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/google-research officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
akosiorek/stacked_capsule_autoencoders officialmentioned on GitHubtfApache-2.0Syntology: 7 samples, 3 ran (0 instrument-failed) · 4 unverified report
KohavTal/SCAE_Project mentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 16 ran (1 instrument-failed) · 0 unverified report
MuhammadMomin93/Stacked-Capsule-Autoencoders-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
Victor-Martinez-Pozos/stacked_capsule_autoencoders mentioned on GitHubtfSyntology: not harvested report
YuZiHanorz/stacked_capsule_autoencoders mentioned on GitHubtfApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ara-25/MSDS19002_Project_DLSpring2020 mentioned on GitHubpytorchSyntology: not harvested report
bdsaglam/torch-scae mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
benenzhu/version0.3-scae mentioned on GitHubpytorchSyntology: not harvested report
cxiang26/stacked_capsule_autoencode_pl mentioned on GitHubpytorchSyntology: not harvested report
phanideepgampa/stacked-capsule-networks mentioned on GitHubpytorchSyntology: not harvested report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

29 samples harvested: 25 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 1 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
23ran
4unverified

Licence: 1 of the 29 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

akosiorek/stacked_capsule_autoencoders official repository 7 samples, 3 ran (0 instrument-failed) · 4 unverified
hex_to_rgb in 6 papers capsules/plot.py ran fingerprinted Apache-2.0 (permissive) · 4c1d49543510213d · report fixture: signature value:str/0/str · returned tuple · level recorded 2026-09-25
memoize_arg_transform capsules/models/model.py ran Apache-2.0 (permissive) · 8c55f32be627e0ca · report fixture: signature args:tuple/1/int, kwargs:dict/0/? · returned tuple · level recorded 2026-09-25
relu1 capsules/math_ops.py ran fingerprinted Apache-2.0 (permissive) · 7ac5d15a4e829dd7 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
gaussian_blobs capsules/plot.py unverified Apache-2.0 (permissive) · c94d19b7ab25522a · report
gaussian_blobs_const_scale capsules/plot.py unverified Apache-2.0 (permissive) · 8e494526a6edfb93 · report
safe_ce capsules/math_ops.py unverified Apache-2.0 (permissive) · 094969771f521bf6 · report
KohavTal/SCAE_Project community (archive-listed) 16 samples, 16 ran (1 instrument-failed) · 0 unverified
BestStack torch_scae/nn_ext.py ran Apache-2.0 (permissive) · 3a64054158d703c5 · report fixture: signature in_channels:int/0/int, out_channels:list/1/int, kernel_sizes:list/1/int, strides:list/1/int, activation:callable/0/?, activate_final:bool/0/bool, dropout:float/0/float · returned Sequential · level recorded 2026-09-24
Conv2dStack torch_scae/nn_ext.py ran Apache-2.0 (permissive) · 1f7981add3e51350 · report fixture: signature in_channels:int/0/int, out_channels:list/1/int, kernel_sizes:list/1/int, strides:list/1/int, activation:callable/0/?, activate_final:bool/0/bool · returned Sequential · level recorded 2026-09-24
MLP in 375 papers torch_scae/nn_ext.py ran Apache-2.0 (permissive) · 018f862a3ae6ed96 · report fixture: signature sizes:list/1/int, activation:callable/0/?, activate_final:bool/0/bool, bias:bool/0/bool · returned Sequential · level recorded 2026-09-24
capsule_l2_loss torch_scae/object_decoder.py ran Apache-2.0 (permissive) · dbc3e25948c02028 · report fixture: signature caps_presence:Tensor/2/float, n_classes:int/0/int, within_example_constant:NoneType/0/? · returned tuple · level recorded 2026-09-24
combined_shape in 16 papers torch_scae/general_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 57542f87e248db45 · report fixture: signature length:int/0/int, shape:NoneType/0/? · returned tuple · level recorded 2026-09-22
conv_output_shape in 8 papers torch_scae/nn_utils.py ran Apache-2.0 (permissive) · 46a280d5631eb673 · report fixture: signature input_shape:tuple/1/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int · returned tuple · level recorded 2026-09-24
conv_output_size in 6 papers torch_scae/nn_utils.py ran fingerprinted Apache-2.0 (permissive) · 6c8cdd002826e750 · report fixture: signature in_size:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int · returned int · level recorded 2026-09-24
cross_entropy_safe torch_scae/math_ops.py ran fingerprinted Apache-2.0 (permissive) · f65130ec27f57098 · report fixture: signature true_probs:Tensor/2/float, probs:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
geometric_transform torch_scae/cv_ops.py ran Apache-2.0 (permissive) · eaacf4c75671e1c5 · report fixture: signature pose_tensor:Tensor/2/float, similarity:bool/0/bool, nonlinear:bool/0/bool, as_matrix:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_latest_file_iteration torch_scae/general_utils.py ran Apache-2.0 (permissive) · 7b5f49577ae87818 · report fixture: signature folder:str/0/str, pattern:str/0/str · returned tuple · level recorded 2026-09-24
log_safe torch_scae/math_ops.py ran fingerprinted Apache-2.0 (permissive) · dcc02359a095982c · report fixture: signature tensor:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
measure_shape torch_scae/nn_utils.py ran Apache-2.0 (permissive) · 835457d36160df6b · report fixture: signature network:callable/0/?, input_shape:tuple/1/int, input_dtype:dtype/0/? · returned Size · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
torch_scae/math_ops.py ran fingerprinted Apache-2.0 (permissive) · 557120b6207db13a · report fixture: signature tensor:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
prepare_model_params torch_scae/factory.py ran Apache-2.0 (permissive) · 114ca279f4f910b1 · report fixture: signature image_shape:tuple/1/int, n_classes:int/0/int, n_part_caps:int/0/int, n_obj_caps:int/0/int, pcae_cnn_encoder_params:NoneType/0/?, pcae_encoder_params:NoneType/0/?, pcae_template_generator_params:NoneType/0/?, pcae_decoder_params:NoneType/0/?, ocae_encoder_set_transformer_params:NoneType/0/?, ocae_decoder_capsule_params:NoneType/0/?, scae_params:NoneType/0/? · returned dict · level recorded 2026-09-24
prod in 40 papers torch_scae/general_utils.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 6d5acfb0087d1ee7 · report fixture: signature iterable:list/1/int · returned int · level recorded 2026-09-22
qkv_attention torch_scae/set_transformer.py ran Apache-2.0 (permissive) · 11fd17f376687a4c · report fixture: signature queries:Tensor/3/float, keys:Tensor/3/float, values:Tensor/3/float, presence:Tensor/2/float · returned Tensor · level recorded 2026-09-24
YuZiHanorz/stacked_capsule_autoencoders community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
load_data_from_mat load_affnist.py ran Apache-2.0 (permissive) · dba87d282c88c543 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
toNum handle_csv.py ran Apache-2.0 (permissive) · a0c52efb1af7f6d5 · report fixture: signature str:str/0/str · returned tuple · level recorded 2026-09-24
bdsaglam/torch-scae community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
BatchMLP torch_scae/nn_ext.py ran Apache-2.0 (permissive) · d6debf9640bd00f2 · report fixture: signature n_mlps:int/0/int, sizes:list/1/int, activation:callable/0/?, activate_final:bool/0/bool, bias_final:bool/0/bool · returned Sequential · level recorded 2026-09-24
affine_grid torch_scae/part_decoder.py ran Apache-2.0 (permissive) · 7972654ad56da3c4 · report fixture: signature matrix:Tensor/2/float, size:tuple/1/int · returned Tensor · level recorded 2026-09-24
geometric_transform torch_scae/cv_ops.py ran Apache-2.0 (permissive) · aee48248137bef44 · report fixture: signature pose_tensor:Tensor/2/float, similarity:bool/0/bool, nonlinear:bool/0/bool, as_matrix:bool/0/bool · returned Tensor · level recorded 2026-09-24
invert_affine torch_scae/part_decoder.py ran Apache-2.0 (permissive) · 00f1c79b7fde1b74 · report fixture: signature matrix:Tensor/3/float · returned Tensor · level recorded 2026-09-24

Tasks

Cross-Modal RetrievalObjectUnsupervised MNIST

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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