SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.04581 · 2020

Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2004.04581.json · badge: /api/ran/2004.04581.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
YudeWang/SEAM canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
adaptive_min_pooling_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from Carlisle-Liu/SBNet
pointer only · get_code("4c323e44c38f5fb2")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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_python_eval Ran
ran; our contract draft was wrong, not the code
YudeWang/SEAM/evaluation.py
code served (permissive licence) · get_code("4de99c8ad78aceee")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import numpy as np
from PIL import Image
import tempfile
import shutil

# Create temporary directories for predict and gt folders
temp_dir = tempfile.mkdtemp()
predict_folder = os.path.join(temp_dir, 'predict')
gt_folder = os.path.join(temp_dir, 'gt')
os.makedirs(predict_folder, exist_ok=True)
os.makedirs(gt_folder, exist_ok=True)

# Create sample PNG prediction and ground truth files
name_list = ['sample_1', 'sample_2', 'sample_3']

for name in name_list:
    # Create prediction images (21 classes, 64x48 resolution)
    predict_array = np.random.randint(0, 21, size=(64, 48), dtype=np.uint8)
    predict_img = Image.fromarray(predict_array, mode='L')
    predict_img.save(os.path.join(predict_folder, f'{name}.png'))
    
    # Create ground truth images (same size, with some pixels set to 255 for ignore)
    gt_array = np.random.randint(0, 21, size=(64, 48), dtype=np.uint8)
    # Add some ignore pixels (255)
    gt_array[0:5, 0:5] = 255
    gt_img = Image.fromarray(gt_array, mode='L')
    gt_img.save(os.path.join(gt_folder, f'{name}.png'))

ARGS = {
    'predict_folder': predict_folder,
    'gt_folder': gt_folder,
    'name_list': name_list,
    'num_cls': 21,
    'input_type': 'png',
    'threshold': 1.0,
    'printlog': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
max_onehot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from Carlisle-Liu/SBNet
pointer only · get_code("a9c8bd4002c21246")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
adaptive_min_pooling_loss 3 other papers
1 dated earlier, 2 later
1903.00179 (2019-03)
Pyramid Feature Attention Network for Saliency detection
2104.07216 (2021-04)
Learning structure-aware semantic segmentation with image-level supervision
2108.03852 (2021-08)
Complementary Patch for Weakly Supervised Semantic Segmentation
max_onehot 2 other papers
1 dated earlier, 1 later
1903.00179 (2019-03)
Pyramid Feature Attention Network for Saliency detection
2104.07216 (2021-04)
Learning structure-aware semantic segmentation with image-level supervision
do_python_eval 1 other paper
1 later
2108.03852 (2021-08)
Complementary Patch for Weakly Supervised 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due to the gap between full and weak supervisions. In this paper, we propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation. However, this constraint is lost on the CAMs trained by image-level supervision. Therefore, we propose consistency regularization on predicted CAMs from various transformed images to provide self-supervision for network learning. Moreover, we propose a pixel correlation module (PCM), which exploits context appearance information and refines the prediction of current pixel by its similar neighbors, leading to further improvement on CAMs consistency. Extensive experiments on PASCAL VOC 2012 dataset demonstrate our method outperforms state-of-the-art methods using the same level of supervision. The code is released online.

For agents

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

get_harvested_code_for_paper("2004.04581")
get_code_for_paper("2004.04581")
have("2004.04581")

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

curl https://syntology.ai/api/ran/2004.04581.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.04581.svg)](https://syntology.ai/paper/2004.04581)

Connect an agent — have() is free.