Methods › Computer Vision › Vision Transformers › NesT

NesT

37 papers tagged archive 2025-07-28

Introduced by Zizhao Zhang et al. in Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding

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

NesT stacks canonical transformer layers to conduct local self-attention on every image block independently, and then "nests" them hierarchically. Coupling of processed information between spatially adjacent blocks is achieved through a proposed block aggregation between every two hierarchies. The overall hierarchical structure can be determined by two key hyper-parameters: patch size S × S and number of block hierarchies T_d. All blocks inside each hierarchy share one set of parameters. Given input of image, each image is linearly projected to an embedding. All embeddings are partitioned to blocks and flattened to generate final input. Each transformer layers is composed of a multi-head self attention (MSA) layer followed by a feed-forward fully-connected network (FFN) with skip-connection and Layer normalization. Positional embeddings are added to encode spatial information before feeding into the block. Lastly, a nested hierarchy with block aggregation is built -- every four spatially connected blocks are merged into one.

PaperSource

In Syntology about another paper, arXiv:2303.05955: repository known, no verified implementation (declared_code; repositories: 5 listed of 5 in the graph, strongest link: official). The lookup matched 'NEST' ignoring case. About another paper: this answer is about arXiv:2303.05955, while the archive credits arXiv:2105.12723.

From the lookup's note on this name: The same name also belongs to the paper “NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm” (arXiv:1711.02017, 258 citations), which the lookup finds cited far more than the paper this answer is about (69 citations), so this answer may be about a different sense of the name. For arXiv:1711.02017: ask the lookup about it.

Origin paper of this answer, arXiv:2303.05955 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 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: 37 · with a code link: 13 · where Syntology ran a sample: 3 (3 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 (3 of 37 tagged: 3 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 37 of 37, 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 35 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
regression3
Image Classification2
Object2
Prediction2
Anatomy1
Anomaly Detection1
Audio Denoising1
Autonomous Driving1
BIG-bench Machine Learning1
Benchmarking1
Decision Making1
Decoder1
Deep Learning1
Denoising1
Domain Generalization1
Event Detection1
Evolutionary Algorithms1
GPU1
Image Generation1
In-Context Learning1

Usage over time archive 2025-07-28

Papers per year tagged with NesT: 2021 to 2025, peak 12 12 0 2021: 5 papers 2021 2022: 7 papers 2022 2023: 10 papers 2023 2024: 12 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (37 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 Transformers

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