Papers › Spatial Transformer Networks

Spatial Transformer Networks

5 Jun 2015NeurIPS 2015 12arXiv:1506.02025archive 2025-07-28

Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network. This differentiable module can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimisation process. We show that the use of spatial transformers results in models which learn invariance to translation, scale, rotation and more generic warping, resulting in state-of-the-art performance on several benchmarks, and for a number of classes of transformations.

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 31 code samples harvested from 6 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 31 samples from 6 repositories, 21 ran (20 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 6 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

45 repositories listed; official and paper-mentioned ones first.

AndreiMoraru123/PointNet mentioned on GitHubpytorchSyntology: not harvested report
FingerRec/DSM mentioned on GitHubpytorchSyntology: not harvested report
HelioStrike/Spatial-Transformation-Network mentioned on GitHubpytorchSyntology: not harvested report
IBM/MAX-Spatial-Transformer-Network mentioned on GitHubtfApache-2.0Syntology: not harvested report
Legend94rz/spatial-transformer mentioned on GitHubtfSyntology: not harvested report
Mugilvanan/stnbhwd mentioned on GitHubMITSyntology: not harvested report
N0Wire/Traffic-Sign-Detection mentioned on GitHubpytorchSyntology: not harvested report
SkafteNicki/ddtn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
Sooram/cnn mentioned on GitHubtfSyntology: not harvested report
Sooram/stn mentioned on GitHubtfSyntology: not harvested report
TencentYoutuResearch/SelfSupervisedLearning-DSM mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
breadbread1984/SpatialTransformLayer-tf2.0 mentioned on GitHubtfSyntology: not harvested report
chenwuperth/rgz_rcnn mentioned on GitHubtfMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
dabane-ghassan/int-lab-book mentioned on GitHubpytorchMITSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
darr/spatial_transformer_networks mentioned on GitHubpytorchSyntology: not harvested report
dicksiano/Spatial-Transformer-Network mentioned on GitHubpytorchSyntology: not harvested report
elisiojsj/Kuzushiji-49 mentioned on GitHubpytorchSyntology: not harvested report
eonr/CompVision mentioned on GitHubpytorchSyntology: not harvested report
fingerrec/dsm-decoupling-scene-motion mentioned on GitHubpytorchSyntology: not harvested report
gjp1203/LIV360SV mentioned on GitHubtfSyntology: not harvested report
iwyoo/tf_thinplatespline mentioned on GitHubtfApache-2.0Syntology: 2 samples, 0 ran · 2 unverified report
jun0wanan/stnbhwd mentioned on GitHubMITSyntology: not harvested report
kaushal-k/Deep-Emotion mentioned on GitHubtfSyntology: not harvested report
kevinzakka/spatial-transformer-network mentioned on GitHubtfMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
kinik93/Spatial-Transformer-Network-application mentioned on GitHubtfMITSyntology: not harvested report
leongkhing/stnbhwd mentioned on GitHubMITSyntology: not harvested report
maxmatical/pytorch-projects mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
mimikaan/Attention-Model mentioned on GitHubtfMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
minoring/spatial-transformer-net mentioned on GitHubtfSyntology: not harvested report
moodstocks/gtsrb.torch mentioned on GitHubtorchMITSyntology: not harvested report
mp31192/3D-SpatialTransformationLayer-pytorch mentioned on GitHubpytorchSyntology: not harvested report
oarriaga/spatial_transformer_networks mentioned on GitHubtfMITSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
ppriyank/Deep-neural-network-for-traffic-sign-recognition-systems mentioned on GitHubpytorchSyntology: not harvested report
renato145/stn mentioned on GitHubpytorchSyntology: not harvested report
sayakpaul/Spatial-Transformer-Networks-with-Keras mentioned on GitHubApache-2.0Syntology: not harvested report
sbillburg/CRNN-with-STN mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its... (arXiv:1507.05717; that paper's own run record: 66 ran (of which 0 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 1 violated, 47 with no contract checked; 17 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
shubhtuls/stn3d mentioned on GitHubMITSyntology: not harvested report
tensorpack/tensorpack mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (arXiv:1511.06434; that paper's own run record: 128 ran (of which 61 constructed an object rather than computing a result; 111 with no instrument failure: 3 honoured, 0 violated, 108 with no contract checked; 17 where Syntology's instrument failed) · 91 unverified) and Improved Training of Wasserstein GANs (arXiv:1704.00028; that paper's own run record: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
tianyu-tristan/Visual-Attention-Model mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Recurrent Models of Visual Attention (arXiv:1406.6247; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 2 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
uam-biometrics/Transformer-Networks mentioned on GitHubpytorchSyntology: not harvested report
vicsesi/PyTorch-STN mentioned on GitHubpytorchSyntology: not harvested report
vinod377/STN-OCR mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
vinod377/STN-OCR-Tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
vkumaresan/Rotational-CoordConv mentioned on GitHubSyntology: 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

31 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
1ran · our draft was wrong
16ran
10unverified

Licence: 0 of the 31 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 6 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.

chenwuperth/rgz_rcnn community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
bbox_transform in 11 papers lib/fast_rcnn/bbox_transform.py ran fingerprinted MIT (permissive) · e774ae94b0630877 · report fixture: signature ex_rois:ndarray/2/float, gt_rois:ndarray/2/float · returned ndarray · level recorded 2026-09-26
bbox_transform_inv in 11 papers lib/fast_rcnn/bbox_transform.py ran · honoured contract fingerprinted MIT (permissive) · b3695ebe0c382b05 · report fixture: signature boxes:ndarray/2/float, deltas:ndarray/2/float · returned ndarray · level recorded 2026-09-22
clip_boxes in 10 papers lib/fast_rcnn/bbox_transform.py ran fingerprinted MIT (permissive) · d24c99284beca7a6 · report fixture: signature boxes:ndarray/2/float, im_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
unique_boxes in 21 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · 8a015c012f507631 · report fixture: signature boxes:ndarray/2/float, scale:float/0/float · returned ndarray · level recorded 2026-09-26
xywh_to_xyxy in 24 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · d3e019b11b709edb · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
xyxy_to_xywh in 23 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · a832e5017f504280 · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
get_imdb in 22 papers lib/datasets/factory.py unverified MIT (permissive) · 9f3cea1708a8a9db · report
get_output_dir in 18 papers lib/fast_rcnn/config.py unverified MIT (permissive) · 4786edbc775d299d · report
dabane-ghassan/int-lab-book community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
inverse_pyramid src/POLO/PYramid2.py ran MIT (permissive) · bfe7459e545240af · report fixture: signature img_crop:Tensor/5/float, N_X:int/0/int, N_Y:int/0/int, base_levels:int/0/int, color:bool/0/bool, verbose:bool/0/bool, gauss:bool/0/bool, n_levels:NoneType/0/?, color_test:bool/0/bool · returned Tensor · level recorded 2026-09-26
minmax in 12 papers src/what_where/display.py ran fingerprinted MIT (permissive) · 55cf5bb59b4c12a8 · report fixture: signature value:float/0/float, border:float/0/float · returned float · level recorded 2026-09-26
test in 377 papers src/what_where/what.py ran MIT (permissive) · a5fa28bbc8a62fb2 · report fixture: signature args:NoneType/0/?, model:callable/0/?, device:device/0/?, test_loader:TestLoaderWrapper/0/?, loss_function:callable/0/? · returned float · level recorded 2026-09-26
test in 377 papers src/what_where/where.py ran MIT (permissive) · 6da6edb8aece76fb · report fixture: signature args:dict/0/?, model:callable/0/?, device:device/0/?, test_loader:list/1/tuple, loss_function:callable/0/? · returned float · level recorded 2026-09-26
update_results src/what_where/params.py ran MIT (permissive) · e821564998838029 · report fixture: signature results:dict/0/?, parameter:str/0/str, accuracies:dict/0/?, ci:float/0/float · returned dict · level recorded 2026-09-26
view_data src/utils.py ran MIT (permissive) · 1d6d0f48d1aff5b7 · report fixture: signature data:Tensor/4/float, label:Tensor/1/int, n:int/0/int · returned Figure · level recorded 2026-09-26
view_data_rand src/utils.py ran MIT (permissive) · a174d68d46e60b26 · report fixture: signature loader:DataLoader/0/?, n:int/0/int · returned Figure · level recorded 2026-09-26
where_suffix src/what_where/where.py ran MIT (permissive) · 0dfdbaf4296b86c7 · report fixture: signature args:Namespace/0/? · returned str · level recorded 2026-09-26
MotionCloudNoise src/what_where/display.py unverified MIT (permissive) · 79325aefec89c096 · report
color_encode src/POLO/PYramid2.py unverified MIT (permissive) · eb493f3004a0f740 · report
get_data_loader in 44 papers src/what_where/display.py unverified MIT (permissive) · 5852a12af5d2eee4 · report
iwyoo/tf_thinplatespline community (archive-listed) 2 samples, 0 ran · 2 unverified
ThinPlateSpline ThinPlateSpline.py unverified Apache-2.0 (permissive) · 8021de30a8d4e788 · report
ThinPlateSpline2 ThinPlateSpline2.py unverified Apache-2.0 (permissive) · 273b53d53de15ad7 · report
kevinzakka/spatial-transformer-network community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
affine_grid_generator stn/transformer.py ran MIT (permissive) · 4da47c257ee7f2d5 · report fixture: signature height:int/0/int, width:int/0/int, theta:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-26
array2img utils.py ran MIT (permissive) · 8d48f06c0172ba12 · report fixture: signature x:ndarray/3/float · returned Image · level recorded 2026-09-26
deg2rad in 6 papers utils.py ran fingerprinted MIT (permissive) · 37ca698729436046 · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-26
img2array utils.py ran MIT (permissive) · 0636d4c4d3190d02 · report fixture: signature data_path:str/0/str, desired_size:tuple/1/int, expand:bool/0/bool, view:bool/0/bool · returned ndarray · level recorded 2026-09-26
spatial_transformer_network stn/transformer.py ran MIT (permissive) · f091d5b52d603b24 · report fixture: signature input_fmap:EagerTensor/4/float, theta:EagerTensor/3/float, out_dims:tuple/1/int · returned EagerTensor · level recorded 2026-09-26
get_pixel_value in 6 papers stn/transformer.py unverified MIT (permissive) · aee541a70e048281 · report
mimikaan/Attention-Model community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
bias_variable in 24 papers MNIST/ram/utils.py ran MIT (permissive) · 4c60a7a3b18a04ae · report fixture: signature shape:tuple/1/int · returned ResourceVariable · level recorded 2026-09-26
weight_variable in 29 papers MNIST/ram/utils.py unverified MIT (permissive) · 9de931a21d52f0d1 · report
oarriaga/spatial_transformer_networks community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_initial_weights src/models/utils.py ran · our draft was wrong MIT (permissive) · 254c0867f0a6fecb · report fixture: signature output_size:int/0/int · returned list · level recorded 2026-09-24
STN src/models/STN.py unverified MIT (permissive) · fea0ac5e46a518e4 · report

Tasks

Translation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Spatial Transformer

ConvolutionSGDSpatial Transformer

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