Papers › MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers

MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers

5 Jul 2023arXiv:2307.02321archive 2025-07-28

Jakob Drachmann Havtorn, Amelie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi

The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, processing uniform background areas of an image should not necessitate as much compute as dense, cluttered areas. To address this issue, we propose a dynamic mixed-scale tokenization scheme for ViT, MSViT. Our method introduces a conditional gating mechanism that selects the optimal token scale for every image region, such that the number of tokens is dynamically determined per input. In addition, to enhance the conditional behavior of the gate during training, we introduce a novel generalization of the batch-shaping loss. We show that our gating module is able to learn meaningful semantics despite operating locally at the coarse patch-level. The proposed gating module is lightweight, agnostic to the choice of transformer backbone, and trained within a few epochs with little training overhead. Furthermore, in contrast to token pruning, MSViT does not lose information about the input, thus can be readily applied for dense tasks. We validate MSViT on the tasks of classification and segmentation where it leads to improved accuracy-complexity trade-off.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.02321")

Code

Syntology Ran 8 of 8 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

qualcomm-ai-research/batchshaping officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 8 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran

Licence: 8 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qualcomm-ai-research/batchshaping. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_normal_cdf qualcomm-ai-research/batchshaping/batchshaping/cdf_normal.py official repository ran fingerprinted licence not identified · pointer only · 65c95846070f4562 · report
get_relaxed_bernoulli_cdf qualcomm-ai-research/batchshaping/batchshaping/cdf_relaxedbernoulli.py official repository ran fingerprinted licence not identified · pointer only · 2ff74f6eac0c1d2e · report
get_relaxed_bernoulli_pdf qualcomm-ai-research/batchshaping/batchshaping/cdf_relaxedbernoulli.py official repository ran fingerprinted licence not identified · pointer only · 8f0e248c0dd763e3 · report
init_anim_plot qualcomm-ai-research/batchshaping/batchshaping/viz_utils.py official repository ran licence not identified · pointer only · e880f7dc0d93c7c5 · report
init_gbas_anim_plot qualcomm-ai-research/batchshaping/batchshaping/viz_utils.py official repository ran licence not identified · pointer only · dc04c9c7a65027eb · report
to_numpy qualcomm-ai-research/batchshaping/batchshaping/utils.py official repository ran licence not identified · pointer only · 1c78c301af20fc6f · report
validate_prior_param qualcomm-ai-research/batchshaping/batchshaping/utils.py official repository ran licence not identified · pointer only · 737717d0bd22c5fb · report
warmup_factory qualcomm-ai-research/batchshaping/batchshaping/utils.py official repository ran licence not identified · pointer only · e9256d0acc5a36e8 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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