SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.01948 · ICCV · 2021

Robust Trust Region for Weakly Supervised Segmentation

Dmitrii Marin, Yuri Boykov

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2104.01948.json · badge: /api/ran/2104.01948.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
dmitrii-marin/robust_trust_region community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
BilinearPottsRelaxation Ran
ran on a synthesized input
dmitrii-marin/robust_trust_region/pytorch-deeplab_v3_plus/GridCRFLoss.py
code served (permissive licence) · get_code("8bcf0e53ecee8d98")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch
import numpy as np

# BilinearPottsRelaxation has no __init__ method (it's a static-method-only class)
# so INIT_ARGS should be empty
INIT_ARGS = {}

# The computation method is 'comute' (note the typo in the original class)
METHOD = 'comute'

# Create arguments for the comute method: a and b
ARGS = {
    'a': torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]),
    'b': torch.tensor([[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]])
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
GridPottsLoss Ran
ran on a synthesized input · constructed an object; no result was computed
dmitrii-marin/robust_trust_region/pytorch-deeplab_v3_plus/GridCRFLoss.py
code served (permissive licence) · get_code("6a56f678c5a53a47")
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 an instance of its own class, GridPottsLoss: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn
import math

torch.manual_seed(0)

# Define the relaxation class (already provided in the function signature)
class BilinearPottsRelaxation(object):
    @staticmethod
    def comute(a, b):
        return a * (1 - b)

# Create small tensors for the forward pass
batch_size = 2
channels = 3
height = 4
width = 5

# images: (batch, channels, height, width)
images = torch.randn(batch_size, channels, height, width)

# segmentations: (batch, 1, height, width) - single channel segmentation
segmentations = torch.randn(batch_size, 1, height, width)

# ROIs: (batch, height, width) - 2D mask
ROIs = torch.ones(batch_size, height, width)

# Define constructor parameters
weight = 0.5
scale_factor = 1.0
relaxation = BilinearPottsRelaxation
neighbourhood = 8

ARGS = {
    'weight': weight,
    'scale_factor': scale_factor,
    'relaxation': relaxation,
    'neighbourhood': neighbourhood,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GridPottsLoss — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GridPottsLoss 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is labeled or when only image-level tags are available. It has been shown that regularized losses-originally developed for unsupervised low-level segmentation and representing geometric priors on pixel labels-can considerably improve the quality of weakly supervised training. However, many common priors require optimization stronger than gradient descent. Thus, such regularizers have limited applicability in deep learning. We propose a new robust trust region approach 1 for regularized losses improving the state-of-theart results. Our approach can be seen as a higher-order generalization of the classic chain rule. It allows neural network optimization to use strong low-level solvers for the corresponding regularizers, including discrete ones.

For agents

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

get_harvested_code_for_paper("2104.01948")
get_code_for_paper("2104.01948")
have("2104.01948")

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

curl https://syntology.ai/api/ran/2104.01948.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.01948.svg)](https://syntology.ai/paper/2104.01948)

Connect an agent — have() is free.