Methods › Computer Vision › Vision Transformers › TNT

Transformer in Transformer

TNT

12 papers tagged archive 2025-07-28

Introduced by Kai Han et al. in Transformer in Transformer

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

Transformer is a type of self-attention-based neural networks originally applied for NLP tasks. Recently, pure transformer-based models are proposed to solve computer vision problems. These visual transformers usually view an image as a sequence of patches while they ignore the intrinsic structure information inside each patch. In this paper, we propose a novel Transformer-iN-Transformer (TNT) model for modeling both patch-level and pixel-level representation. In each TNT block, an outer transformer block is utilized to process patch embeddings, and an inner transformer block extracts local features from pixel embeddings. The pixel-level feature is projected to the space of patch embedding by a linear transformation layer and then added into the patch. By stacking the TNT blocks, we build the TNT model for image recognition.

Image source: Han et al.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 11 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Transformer in Transformer (TNT)' (resolution: alias); this answer is about that name. This answer is about arXiv:2103.00112, the paper the archive credits with this method.

Origin paper of this answer, arXiv:2103.00112 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified (of 24 harvested samples) · 5 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

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: 12 · with a code link: 5 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 12 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 12 of 12, 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

14 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
Image Classification2
Second-order methods2
Sentence2
3DGS1
Autonomous Vehicles1
Deep Learning1
Evolutionary Algorithms1
Fine-Grained Image Classification1
Image Harmonization1
NeRF1
Neural Rendering1
Surface Reconstruction1
Traffic Sign Recognition1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with TNT: 2021 to 2024, peak 6 6 0 2021: 4 papers 2021 2022: 2 papers 2022 2023: 0 papers 2023 2024: 6 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (12 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

Vision TransformersImage Model BlocksImage ModelsBackbone ArchitecturesTransformers

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