Browse State-of-the-Art › Efficient ViTs
Efficient ViTs
27 papers with code · 3 benchmarks · 0 datasets archive 2025-07-28
Increasing the efficiency of ViTs without the modification of the architecture. (i.e., Key & Query Sparsification, Token pruning & merging)
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “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. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 32 · with a code link: 27 · where Syntology ran a sample: 22 (18 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (22 of 32 tagged: 18 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 32 of 32, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “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 figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
23 Dec 2020 40 repositories listed Syntology community repositories only · 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 19 harvested samples) · 3 pointer-only (licence)In this work, we produce a competitive convolution-free transformer by training on Imagenet only.
-
22 Apr 2021 7 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 3 pointer-only (licence)In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs).
-
17 Oct 2022 5 repositories listed Syntology official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 4 pointer-only (licence)Off-the-shelf, ToMe can 2x the throughput of state-of-the-art ViT-L @ 512 and ViT-H @ 518 models on images and 2.
-
26 May 2022 5 repositories listed Syntology official (archive's flag): 1 ran · 11 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 13 harvested samples) · 2 pointer-only (licence)Therefore, we propose to disentangle the high/low frequency patterns in an attention layer by separating the heads into two groups, where one group encodes high frequencies via self-attention within each local window…
-
18 Nov 2022 4 repositories listedVision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities…
-
23 Nov 2021 3 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples)Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers.
-
3 Oct 2023 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 2 pointer-only (licence)Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks.
-
5 Jul 2023 2 repositories listedNaivly combining datasets from different domains can result in negative knowledge transfer (NKT), i. e., a decrease in model performance on some domains with non-negligible inter-domain heterogeneity.
-
16 Feb 2022 2 repositories listed Syntology official (archive's flag): 10 ran · 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples) · 12 pointer-only (licence)Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images.
-
3 Jun 2021 2 repositories listed Syntology official (archive's flag): 5 ran · 7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 1 pointer-only (licence)Based on this observation, we propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input.
-
19 Mar 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result (of 2 harvested samples)However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and lacks hierarchical representation.
-
6 May 2024 1 repository listedMotivated by the huge success of Transformers in the field of natural language processing (NLP), Vision Transformers (ViTs) have been rapidly developed and achieved remarkable performance in various computer vision…
-
15 Mar 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss.
-
6 Nov 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands.
-
20 Jul 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years.
-
10 Jun 2023 1 repository listed Syntology official (archive's flag): 14 ran · 14 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified (of 20 harvested samples) · 2 pointer-only (licence)To marry the best of both worlds, we further propose a new mixture of experts (MoE) framework to reparameterize MLPs by taking multiplication or its primitives as experts, e. g., multiplication and shift, and designing…
-
29 May 2023 1 repository listedToken compression aims to speed up large-scale vision transformers (e. g.
-
21 Apr 2023 1 repository listed Syntology 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) · 4 unverified (of 8 harvested samples) · 1 pointer-only (licence)Experiments on various transformers demonstrate the effectiveness of our method, while analysis experiments prove our higher robustness to the errors of the token pruning policy.
-
15 Mar 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 4 harvested samples)In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks.
-
21 Nov 2022 1 repository listedIn this paper, we emphasize the cruciality of diverse global semantics and propose an efficient token decoupling and merging method that can jointly consider the token importance and diversity for token pruning.
-
28 Sep 2022 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)The learnable thresholds are optimized in budget-aware training to balance accuracy and complexity, performing the corresponding pruning configurations for different input instances.
-
27 Dec 2021 1 repository listed Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Moreover, our framework can guarantee the identified model to meet resource specifications of mobile devices and FPGA, and even achieve the real-time execution of DeiT-T on mobile platforms.
-
14 Dec 2021 1 repository listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
-
30 Nov 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training.
-
10 Oct 2021 1 repository listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)This work aims on challenging the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage, where we redistribute the parameters both across…
-
3 Aug 2021 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 1 pointer-only (licence)Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue.
-
8 Jun 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 7 harvested samples)For example, our sparsified DeiT-Small at (5%, 50%) sparsity for (data, architecture), improves 0.
-
ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition21 Dec 2024 0 repositories listedVision Transformers (ViTs) have achieved remarkable success in various computer vision tasks.
-
M²-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization10 Oct 2024 0 repositories listedAlthough Vision Transformers (ViTs) have achieved significant success, their intensive computations and substantial memory overheads challenge their deployment on edge devices.
-
An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT29 Mar 2024 0 repositories listedVision Transformers (ViTs) have achieved significant success in computer vision.
-
23 Jun 2021 0 repositories listed
-
5 Jun 2021 0 repositories listed
Syntology lines on 22 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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