SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.02853 · 2021

Reliable Propagation-Correction Modulation for Video Object Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 1 violated it and 3 have no contract verdict; 1 failure of our instrument; 0 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/2112.02853.json · badge: /api/ran/2112.02853.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
jerryx1110/rpcmvos canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
all_to_onehot Ran
ran, violated the contract we drafted
jerryx1110/rpcmvos/dataloaders/datasets.py
pointer only (licence: MIT); the stored copy get_code serves, from jerryx1110/robust-video-object-segmentation, is pointer only (licence: NONE) · get_code("7221953c05ccc6b9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jerryx1110/robust-video-object-segmentation, and GitHub detected no licence in that repository 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.

build_aspp Ran
ran; our contract draft was wrong, not the code
jerryx1110/rpcmvos/networks/deeplab/aspp.py
code served (permissive licence) · get_code("4d0070cfa5e25a53")
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 ASPP. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "backbone": "resnet",
    "output_stride": 16,
    "BatchNorm": nn.BatchNorm2d
}
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 ASPP — a ASPP output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ASPP 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
build_decoder Ran
ran on a synthesized input
jerryx1110/rpcmvos/networks/deeplab/decoder.py
code served (permissive licence) · get_code("def8ad790566e5e1")
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 Decoder. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'backbone': 'resnet',
    'BatchNorm': nn.BatchNorm2d
}
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 Decoder — a Decoder output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Decoder 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
calculate_attention_head Ran
ran on a synthesized input
jerryx1110/rpcmvos/networks/layers/attention.py
code served (permissive licence) · get_code("ca820f23f256da70")
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 Tensor, ndim 2, dtype family float, shape (2, 16) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create tiny tensors with distinct dimensions
# ref_embedding and prev_embedding: shape (batch, channels, height, width)
# ref_label and prev_label: shape (batch, channels, height, width) with binary values
batch_size = 2
channels = 4
height = 3
width = 5

ref_embedding = torch.randn(batch_size, channels, height, width)
ref_label = torch.randint(0, 2, (batch_size, channels, height, width)).float()

prev_embedding = torch.randn(batch_size, channels, height, width)
prev_label = torch.randint(0, 2, (batch_size, channels, height, width)).float()

epsilon = 1e-05

ARGS = {
    "ref_embedding": ref_embedding,
    "ref_label": ref_label,
    "prev_embedding": prev_embedding,
    "prev_label": prev_label,
    "epsilon": epsilon
}
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 Tensor, ndim 2, dtype family float, shape (2, 16) — shape (2, 16) as a later run recorded it
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: none by the harness; any seed is in the setup block
calculate_attention_head_for_eval Ran
ran on a synthesized input
jerryx1110/rpcmvos/networks/layers/attention.py
code served (permissive licence) · get_code("79e4aea1f2a0ea7c")
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 Tensor, ndim 2, dtype family float, shape (2, 16) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function expects:
# - ref_embeddings: list of tensors with shape (batch, channels, height, width)
# - ref_labels: list of tensors with shape (batch, channels, height, width) with binary values
# - prev_embedding: tensor with shape (batch, channels, height, width)
# - prev_label: tensor with shape (batch, channels, height, width) with binary values
# - epsilon: float (default 1e-05)

# Create small tensors for ref_embeddings - list of 2 tensors
ref_embeddings = [
    torch.randn(2, 4, 3, 3),  # batch=2, channels=4, height=3, width=3
    torch.randn(2, 4, 3, 3),
]

# Create binary labels for ref_embeddings
ref_labels = [
    torch.randint(0, 2, (2, 4, 3, 3)).float(),
    torch.randint(0, 2, (2, 4, 3, 3)).float(),
]

# Create prev_embedding and prev_label
prev_embedding = torch.randn(2, 4, 3, 3)
prev_label = torch.randint(0, 2, (2, 4, 3, 3)).float()

ARGS = {
    "ref_embeddings": ref_embeddings,
    "ref_labels": ref_labels,
    "prev_embedding": prev_embedding,
    "prev_label": prev_label,
    "epsilon": 1e-05,
}
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 Tensor, ndim 2, dtype family float, shape (2, 16) — shape (2, 16) as a later run recorded it
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: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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, 1 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
build_aspp 6 other papers
6 dated earlier
1802.02611 (2018-02)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
1910.02550 (2019-10)
ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
2010.06349 (2020-10)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
and 3 more not named here
all_to_onehot 1 other paper
1 later
2207.00887 (2022-07)
Towards Robust Video Object Segmentation with Adaptive Object Calibration
build_decoder 1 other paper
1 dated earlier
2010.06349 (2020-10)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration

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

Error propagation is a general but crucial problem in online semi-supervised video object segmentation. We aim to suppress error propagation through a correction mechanism with high reliability. The key insight is to disentangle the correction from the conventional mask propagation process with reliable cues. We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively. Specifically, we assemble the modulators with a cascaded propagation-correction scheme. This avoids overriding the effects of the reliable correction modulator by the propagation modulator. Although the reference frame with the ground truth label provides reliable cues, it could be very different from the target frame and introduce uncertain or incomplete correlations. We augment the reference cues by supplementing reliable feature patches to a maintained pool, thus offering more comprehensive and expressive object representations to the modulators. In addition, a reliability filter is designed to retrieve reliable patches and pass them in subsequent frames. Our model achieves state-of-the-art performance on YouTube-VOS18/19 and DAVIS17-Val/Test benchmarks. Extensive experiments demonstrate that the correction mechanism provides considerable performance gain by fully utilizing reliable guidance. Code is available at: https://github.com/JerryX1110/RPCMVOS.

For agents

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

get_harvested_code_for_paper("2112.02853")
get_code_for_paper("2112.02853")
have("2112.02853")

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

curl https://syntology.ai/api/ran/2112.02853.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.02853.svg)](https://syntology.ai/paper/2112.02853)

Connect an agent — have() is free.