SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.03392 · NeurIPS · 2024

Boosting Unsupervised Segmentation Learning

Francesco Locatello, Paolo Favaro, Alp Eren

arXiv · PDF · Open in the Atlas

Code that ran

17 of 19 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 13 failures of our instrument; 2 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/2404.03392.json · badge: /api/ran/2404.03392.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
alperensari/segmentation-tricks canonical (classifier label)
classifier basis: census
17 ran · 2 no recorded run
FunctionStatusWhere it lives
IoU Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/token_metric.py
pointer only (licence: NONE) · get_code("cd99c956249eb47c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

IoU_order Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/token_metric.py
pointer only (licence: NONE) · get_code("cf664ed7f1a2e9f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

IoU_seperate Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/token_metric.py
pointer only (licence: NONE) · get_code("aadbae972a4e58c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

boxfilter2d Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/boxfilter.py
pointer only (licence: NONE) · get_code("d4def6521d962d05")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

clip_gradients Ran
ran, honoured the contract we drafted
alperensari/segmentation-tricks/utils.py
pointer only (licence: NONE) · get_code("2b5489053b222e00")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

cosine_scheduler Ran
ran, honoured the contract we drafted
alperensari/segmentation-tricks/utils.py
pointer only (licence: NONE) · get_code("361a6b24f11fc50a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alperensari/segmentation-tricks/vision_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("55120f2026b56aa2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

get_color_distortion Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/utils_dis.py
pointer only (licence: NONE) · get_code("b8ef2b49a369cb69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

get_dino_output_tokens Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/utils_train.py
pointer only (licence: NONE) · get_code("cf9876427eafee4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

get_vec_sim_loss Ran
ran, honoured the contract we drafted
alperensari/segmentation-tricks/utils_dis.py
pointer only (licence: NONE) · get_code("d3c6ce579cbb603f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

load_pretrained_weights Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/utils.py
pointer only (licence: NONE) · get_code("fc95de71038fb481")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

my_tensor_product Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/guided_filter.py
pointer only (licence: NONE) · get_code("7dfe1c90678dc54a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

norm Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/utils_train.py
pointer only (licence: NONE) · get_code("12de5cf1a9536fef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

normalize_chunks Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/utils_dis.py
pointer only (licence: NONE) · get_code("d31e6305789cbce4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

prep_for_plot Ran
ran; our contract draft was wrong, not the code
alperensari/segmentation-tricks/utils_metric.py
pointer only (licence: NONE) · get_code("6a6e5c247d893c0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alperensari/segmentation-tricks/utils_metric.py
pointer only (licence: NONE) · get_code("d86ef5508de1f079")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

shuffle Ran
ran, honoured the contract we drafted
alperensari/segmentation-tricks/utils_metric.py
pointer only (licence: NONE) · get_code("205e834237bf794c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

crop_my_images Not yet run
unverified (harvested, no recorded run)
alperensari/segmentation-tricks/utils_data.py
pointer only (licence: NONE) · get_code("58706db0d93807d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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.

get_valid_idx Not yet run
unverified (harvested, no recorded run)
alperensari/segmentation-tricks/bilateral_solver.py
pointer only (licence: NONE) · get_code("305f5b498129a2ed")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alperensari/segmentation-tricks 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 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 3 later) and 10 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
drop_path 224 other papers
157 dated earlier, 3 the same month, 56 later, 7 same year, order not determinable, 1 undated · 38 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
and 221 more not named here
cosine_scheduler 37 other papers
27 dated earlier, 9 later, 1 same year, order not determinable
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2103.15375 (2021-03)
AlignMixup: Improving Representations By Interpolating Aligned Features
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
and 34 more not named here
clip_gradients 28 other papers
20 dated earlier, 7 later, 1 same year, order not determinable
2106.09681 (2021-06)
XCiT: Cross-Covariance Image Transformers
2109.13228 (2021-09)
PASS: An ImageNet replacement for self-supervised pretraining without humans
2111.12958 (2021-11)
Self-Distilled Self-Supervised Representation Learning
and 25 more not named here
get_color_distortion 6 other papers
6 dated earlier
2002.05709 (2020-02)
A Simple Framework for Contrastive Learning of Visual Representations
2104.09866 (2021-04)
Distill on the Go: Online knowledge distillation in self-supervised learning
2110.01445 (2021-10)
Robust and Decomposable Average Precision for Image Retrieval
and 3 more not named here
get_valid_idx 4 other papers
4 dated earlier
1905.02722 (2019-05)
Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image
2212.05853 (2022-12)
DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
2212.07834 (2022-12)
Unsupervised Object Localization: Observing the Background to Discover Objects
and 1 more not named here
norm 2 other papers
2 dated earlier
2310.17874 (2023-10)
SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
2403.01482 (2024-03)
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation
resize 2 other papers
2 dated earlier
2203.08414 (2022-03)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
2403.01482 (2024-03)
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation
shuffle 2 other papers
2 dated earlier
2203.08414 (2022-03)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
2403.01482 (2024-03)
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation
prep_for_plot 1 other paper
1 dated earlier
2403.01482 (2024-03)
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation

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

We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we leverage image post-processing techniques such as guided filtering to refine the output masks, improving accuracy while avoiding substantial computational costs. Secondly, we introduce a multi-scale consistency criterion, based on a teacherstudent training scheme. This criterion matches segmentation masks predicted from regions of the input image extracted at different resolutions to each other. Experimental results on several benchmarks used in unsupervised segmentation learning demonstrate the effectiveness of our proposed techniques.

For agents

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

get_harvested_code_for_paper("2404.03392")
get_code_for_paper("2404.03392")
have("2404.03392")

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

curl https://syntology.ai/api/ran/2404.03392.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.03392.svg)](https://syntology.ai/paper/2404.03392)

Connect an agent — have() is free.