SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.19422 · CVPR · 2024

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

Marco Ciccone, Claudia Cuttano, Giuseppe Averta, Politecnico Torino, Niccolò Cavagnero, Gabriele Rosi, Francesca Pistilli, Fabio Cermelli, Def Conv

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 5 failures of our instrument; 1 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/2402.19422.json · badge: /api/ran/2402.19422.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
niccolocavagnero/pem canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
NiccoloCavagnero/PEM community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
LocalRepresentation Ran
ran on a synthesized input
NiccoloCavagnero/PEM/pem/modeling/transformer_decoder/pem_transformer_decoder.py
pointer only (licence: NONE) · get_code("28baf4547c97b344")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NiccoloCavagnero/PEM 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.

PEM_CA Ran
ran on a synthesized input
NiccoloCavagnero/PEM/pem/modeling/transformer_decoder/pem_transformer_decoder.py
pointer only (licence: NONE) · get_code("260da9226b359802")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NiccoloCavagnero/PEM 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.

batch_dice_loss Ran
ran; our contract draft was wrong, not the code
niccolocavagnero/pem/pem/modeling/matcher.py
pointer only (licence: NONE) · get_code("bc2cb481a75c370d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, niccolocavagnero/pem 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.

calculate_uncertainty Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
niccolocavagnero/pem/pem/modeling/criterion.py
pointer only (licence: NONE) · get_code("2dcb8123d89bb1ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, niccolocavagnero/pem 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.

dice_loss Ran
ran; our contract draft was wrong, not the code
niccolocavagnero/pem/pem/modeling/criterion.py
pointer only (licence: NONE) · get_code("89f75e54ff128be0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, niccolocavagnero/pem 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.

nested_tensor_from_tensor_list Ran
ran; our contract draft was wrong, not the code
niccolocavagnero/pem/pem/utils/misc.py
pointer only (licence: NONE) · get_code("58cc9ff3bf75e753")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, niccolocavagnero/pem 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.

sigmoid_ce_loss Ran
ran; our contract draft was wrong, not the code
niccolocavagnero/pem/pem/modeling/criterion.py
pointer only (licence: NONE) · get_code("d0c61e8dba511aa3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, niccolocavagnero/pem 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.

batch_sigmoid_ce_loss Not yet run
unverified (harvested, no recorded run)
niccolocavagnero/pem/pem/modeling/matcher.py
pointer only (licence: NONE) · get_code("1edd24985036b0bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, niccolocavagnero/pem 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. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 6 later) and 2 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
nested_tensor_from_tensor_list 55 other papers
39 dated earlier, 14 later, 2 same year, order not determinable · 17 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2101.01909 (2021-01)
Line Segment Detection Using Transformers without Edges
and 52 more not named here
dice_loss 46 other papers
33 dated earlier, 12 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 43 more not named here
sigmoid_ce_loss 45 other papers
32 dated earlier, 1 the same month, 11 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 42 more not named here
batch_dice_loss 44 other papers
29 dated earlier, 14 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
batch_sigmoid_ce_loss 44 other papers
29 dated earlier, 1 the same month, 13 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
calculate_uncertainty 34 other papers
23 dated earlier, 1 the same month, 8 later, 2 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.04187 (2022-03)
RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
and 31 more not named here

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

Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility, they obtain outstanding performance in multiple segmentation tasks, such as semantic and panoptic, under a single unified framework. To achieve such impressive performance, these architectures employ intensive operations and require substantial computational resources, which are often not available, especially on edge devices. To fill this gap, we propose Prototype-based Efficient Mask-Former (PEM), an efficient transformer-based architecture that can operate in multiple segmentation tasks. PEM proposes a novel prototype-based cross-attention which leverages the redundancy of visual features to restrict the computation and improve the efficiency without harming the performance. In addition, PEM introduces an efficient multiscale feature pyramid network, capable of extracting features that have high semantic content in an efficient way, thanks to the combination of deformable convolutions and context-based self-modulation. We benchmark the proposed PEM architecture on two tasks, semantic and panoptic segmentation, evaluated on two different datasets, Cityscapes and ADE20K. PEM demonstrates outstanding performance on every task and dataset, outperforming task-specific architectures while being comparable and even better than computationally expensive baselines. Code is available at https://github.com/NiccoloCavagnero/PEM.

For agents

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

get_harvested_code_for_paper("2402.19422")
get_code_for_paper("2402.19422")
have("2402.19422")

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

curl https://syntology.ai/api/ran/2402.19422.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.19422.svg)](https://syntology.ai/paper/2402.19422)

Connect an agent — have() is free.