Methods › Computer Vision › Vision Transformers › NesT
NesT
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.
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.
-
NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN 22 Jun 2025 · 1 repository · arXiv:2506.17870
-
Mixed-feedback oscillations in the foraging dynamics of arboreal turtle ants 15 Apr 2025 · 0 repositories · arXiv:2504.11551
-
Experimental Validation of Distributed Dispatching of Multiple Active Distribution Networks Using the ADMM 19 Mar 2025 · 0 repositories · arXiv:2503.15356
-
Ant Nest Detection Using Underground P-Band TomoSAR 16 Dec 2024 · 0 repositories · arXiv:2412.11865
-
NEST: A Neuromodulated Small-world Hypergraph Trajectory Prediction Model for Autonomous Driving 16 Dec 2024 · 0 repositories · arXiv:2412.11682
-
Argentine ants regulate traffic flow with stopped individuals 9 Dec 2024 · 0 repositories · arXiv:2412.06587
-
Revisiting the Many Instruments Problem using Random Matrix Theory 16 Aug 2024 · 0 repositories · arXiv:2408.08580
-
Performance Prediction of Hub-Based Swarms 9 Aug 2024 · 0 repositories · arXiv:2408.04822
-
Soli-enabled Noncontact Heart Rate Detection for Sleep and Meditation Tracking 8 Jul 2024 · 0 repositories · arXiv:2407.06458
-
NeST: Neural Stress Tensor Tomography by leveraging 3D Photoelasticity 14 Jun 2024 · 0 repositories · arXiv:2406.10212
-
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution 29 May 2024 · 0 repositories · arXiv:2405.19325
-
Direct learning of home vector direction for insect-inspired robot navigation 6 May 2024 · 0 repositories · arXiv:2405.03827
-
LOOPer: A Learned Automatic Code Optimizer For Polyhedral Compilers 18 Mar 2024 · 1 repository · arXiv:2403.11522
-
DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers 25 Feb 2024 · 1 repository · arXiv:2402.16914Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 7 harvested samples)
-
Norm Enforcement with a Soft Touch: Faster Emergence, Happier Agents 29 Jan 2024 · 0 repositories · arXiv:2401.16461
-
Timing decisions as the next frontier for collective intelligence 1 Dec 2023 · 0 repositories · arXiv:2312.02187
-
InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images 2 Nov 2023 · 1 repository · arXiv:2311.01619
-
Robustify and Tighten the Lee Bounds: A Sample Selection Model under Stochastic Monotonicity and Symmetry Assumptions 1 Nov 2023 · 0 repositories · arXiv:2311.00439
-
Interpreting TSLS Estimators in Information Provision Experiments 9 Sep 2023 · 0 repositories · arXiv:2309.04793
-
Finite population effects on optimal communication for social foragers 1 Aug 2023 · 0 repositories · arXiv:2308.00298
-
Inference for relative sparsity 25 Jun 2023 · 1 repository · arXiv:2306.14297
-
Deep Huber quantile regression networks 17 Jun 2023 · 0 repositories · arXiv:2306.10306
-
SuperNeuro: A Fast and Scalable Simulator for Neuromorphic Computing 4 May 2023 · 1 repository · arXiv:2305.02510
-
Physics Symbolic Learner for Discovering Ground-Motion Models Via NGA-West2 Database 23 Mar 2023 · 0 repositories · arXiv:2303.14179
-
Neuron Structure Modeling for Generalizable Remote Physiological Measurement 10 Mar 2023 · 1 repository · arXiv:2303.05955Syntology official (archive's flag): 2 ran · 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)
-
Emergent communication enhances foraging behaviour in evolved swarms controlled by Spiking Neural Networks 16 Dec 2022 · 1 repository · arXiv:2212.08484
-
Uncovering the Dynamics of the Wealth Distribution 24 Nov 2022 · 1 repository · arXiv:2211.15509
-
Interpreting Instrumental Variable Estimands with Unobserved Treatment Heterogeneity: The Effects of College Education 23 Nov 2022 · 0 repositories · arXiv:2211.13132
-
Self-organizing nest migration dynamics synthesis for ant colony systems 8 Oct 2022 · 0 repositories · arXiv:2210.03975
-
TensorIR: An Abstraction for Automatic Tensorized Program Optimization 9 Jul 2022 · 2 repositories · arXiv:2207.04296
-
Efficiently Evolving Swarm Behaviors Using Grammatical Evolution With PPA-style Behavior Trees 29 Mar 2022 · 0 repositories · arXiv:2203.15776
-
End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing 28 Jan 2022 · 1 repository · arXiv:2201.12348
-
A Modular Workflow for Performance Benchmarking of Neuronal Network Simulations 16 Dec 2021 · 1 repository · arXiv:2112.09018
-
Behavioral Foundations of Nested Stochastic Choice and Nested Logit 14 Dec 2021 · 0 repositories · arXiv:2112.07155
-
Anatomy of a superorganism -- structure and growth dynamics of army ant bivouacs 18 Oct 2021 · 0 repositories · arXiv:2110.09017
-
Audio Attacks and Defenses against AED Systems -- A Practical Study 14 Jun 2021 · 0 repositories · arXiv:2106.07428
-
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding 26 May 2021 · 6 repositories · arXiv:2105.12723Syntology official (archive's flag): 9 ran · 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 1 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 26 harvested samples) · 6 pointer-only (licence)
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.
Usage over time archive 2025-07-28
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
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