SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.09936 · CVPR · 2024

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers

Narges Norouzi, Svetlana Orlova

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.09936.json · badge: /api/ran/2406.09936.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
tue-mps/algm-segmenter canonical (classifier label)
classifier basis: census
7 ran · 5 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tue-mps/algm-segmenter/segm/metrics.py
pointer only (licence: NONE) · get_code("2cc3699f9a695af9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tue-mps/algm-segmenter when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dataset_prepare Ran
ran; our contract draft was wrong, not the code
tue-mps/algm-segmenter/segm/flops.py
pointer only (licence: NOASSERTION) · get_code("f63b55edf664ebb2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

do_nothing Ran
ran, honoured the contract we drafted
tue-mps/algm-segmenter/algm/algm/global_merge.py
pointer only (licence: NONE) · get_code("969e8250d805a154")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tue-mps/algm-segmenter when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_colormap Ran
ran, honoured the contract we drafted
tue-mps/algm-segmenter/algm/algm/vis.py
pointer only (licence: NOASSERTION) · get_code("3869ab58c2773dbd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_dataset_validaion_path Ran
ran; our contract draft was wrong, not the code
tue-mps/algm-segmenter/segm/flops.py
pointer only (licence: NOASSERTION) · get_code("6a84e03ae16e5898")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

merge_source Ran
ran; our contract draft was wrong, not the code
tue-mps/algm-segmenter/algm/algm/local_merge.py
pointer only (licence: NOASSERTION) · get_code("7de1b6333a4490bc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_r Ran
ran, honoured the contract we drafted
tue-mps/algm-segmenter/algm/algm/utils.py
pointer only (licence: NOASSERTION) · get_code("94e8f254ce489a4b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

benchmark Not yet run
unverified (harvested, no recorded run)
tue-mps/algm-segmenter/algm/algm/utils.py
pointer only (licence: NOASSERTION) · get_code("eaef07a98678e866")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

conditional_pooling Not yet run
unverified (harvested, no recorded run)
tue-mps/algm-segmenter/algm/algm/local_merge.py
pointer only (licence: NOASSERTION) · get_code("4c1e01e17e20d12d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

make_visualization Not yet run
unverified (harvested, no recorded run)
tue-mps/algm-segmenter/algm/algm/vis.py
pointer only (licence: NOASSERTION) · get_code("9726524f57061ce3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

merge_wavg Not yet run
unverified (harvested, no recorded run)
tue-mps/algm-segmenter/algm/algm/local_merge.py
pointer only (licence: NOASSERTION) · get_code("4b48cbe3332fcb0c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

turbo_matching Not yet run
unverified (harvested, no recorded run)
tue-mps/algm-segmenter/algm/algm/global_merge.py
pointer only (licence: NOASSERTION) · get_code("6c05551946f3b904")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, tue-mps/algm-segmenter (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 5 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
do_nothing 13 other papers
8 dated earlier, 5 later · 4 only as an assembly brick
2210.09461 (2022-10)
Token Merging: Your ViT But Faster
2307.10780 (2023-07)
Learned Thresholds Token Merging and Pruning for Vision Transformers
2310.01812 (2023-10)
PPT: Token Pruning and Pooling for Efficient Vision Transformers
and 10 more not named here
merge_wavg 5 other papers
2 dated earlier, 3 later · 2 only as an assembly brick
2310.19060 (2023-10)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
2404.09490 (2024-04)
Leveraging Temporal Contextualization for Video Action Recognition
2409.01156 (2024-09)
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
and 2 more not named here
parse_r 4 other papers
3 dated earlier, 1 later
2307.10780 (2023-07)
Learned Thresholds Token Merging and Pruning for Vision Transformers
2310.19060 (2023-10)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
2403.09192 (2024-03)
PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation
and 1 more not named here
accuracy 3 other papers
1 dated earlier, 2 later
2105.05633 (2021-05)
Segmenter: Transformer for Semantic Segmentation
2412.10569 (2024-12)
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
benchmark 2 other papers
2 dated earlier
2306.00989 (2023-06)
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
2310.19060 (2023-10)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
merge_source 2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
2404.09490 (2024-04)
Leveraging Temporal Contextualization for Video Action Recognition
2409.01156 (2024-09)
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
generate_colormap 1 other paper
1 dated earlier
2310.19060 (2023-10)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges similar tokens within a small local window and (2) halfway through the network, it merges similar tokens across the entire image. This is motivated by an analysis in which we found that, in those situations, tokens with a high cosine similarity can likely be merged without a drop in segmentation quality. With extensive experiments across multiple datasets and network configurations, we show that ALGM not only significantly improves the throughput by up to 100%, but can also enhance the mean IoU by up to +1.1, thereby achieving a better trade-off between segmentation quality and efficiency than existing methods. Moreover, our approach is adaptive during inference, meaning that the same model can be used for optimal efficiency or accuracy, depending on the application. Code is available at https://tue-mps.github.io/ALGM .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.09936")
get_code_for_paper("2406.09936")
have("2406.09936")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.09936.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.09936.svg)](https://syntology.ai/paper/2406.09936)

Connect an agent — have() is free.