Methods › Computer Vision › Image Model Blocks › Spatial Transformer

Spatial Transformer

169 papers tagged archive 2025-07-28

Introduced by Max Jaderberg et al. in Spatial Transformer Networks

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

A Spatial Transformer is an image model block that explicitly allows the spatial manipulation of data within a convolutional neural network. It gives CNNs 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. Unlike pooling layers, where the receptive fields are fixed and local, the spatial transformer module is a dynamic mechanism that can actively spatially transform an image (or a feature map) by producing an appropriate transformation for each input sample. The transformation is then performed on the entire feature map (non-locally) and can include scaling, cropping, rotations, as well as non-rigid deformations.

The architecture is shown in the Figure to the right. The input feature map U is passed to a localisation network which regresses the transformation parameters θ. The regular spatial grid G over V is transformed to the sampling grid T_θ(G), which is applied to U, producing the warped output feature map V. The combination of the localisation network and sampling mechanism defines a spatial transformer.

PaperSourceSee Code · kevinzakka/spatial-transformer-network

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Spatially-Aware Transformer; word-level spatial transformer; Ring-based Spatial Transformer; Hierarchical Spatial Transformer; Spatial Grouping Transformer Block; Spatial Planning Transformers (SPT); Spatial-Temporal Parallel Transformer; Spatial-Temporal Transformer (STTran).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 169 · with a code link: 73 · where Syntology ran a sample: 12 (9 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (12 of 169 tagged: 9 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 169, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 200 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Object12
Object Detection10
Segmentation10
object-detection10
Decoder9
Image Registration9
Image Classification8
Pose Estimation8
Semantic Segmentation8
image-classification8
Data Augmentation7
General Classification7
Representation Learning7
Image Reconstruction5
Super-Resolution5
Classification4
Face Alignment4
Person Re-Identification4
Scene Text Recognition4
Self-Supervised Learning4

Usage over time archive 2025-07-28

Papers per year tagged with Spatial Transformer: 2015 to 2025, peak 25 25 0 2015: 4 papers 2015 2016: 7 papers 2016 2017: 14 papers 2017 2018: 13 papers 2018 2019: 16 papers 2019 2020: 23 papers 2020 2021: 23 papers 2021 2022: 25 papers 2022 2023: 22 papers 2023 2024: 18 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (169 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

Image Model Blocks

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