SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.06647 · 2019

RANet: Ranking Attention Network for Fast Video Object Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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 10 have no contract verdict; 1 failure 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/1908.06647.json · badge: /api/ran/1908.06647.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
Storife/RANet canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
v1viswan/RANet_modifications community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Data_combinePicNameList Ran
ran on a synthesized input
Storife/RANet/codes/RANet_lib/RANet_DATA_loader.py
code served (permissive licence) · get_code("17c2725831c1b925")
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 torch

torch.manual_seed(0)

# Create sample dataset dictionaries with lists of strings
# (based on function logic: concatenating strings with '+')
dataset1 = {
    'X_train': ['pic1_', 'pic2_'],
    'X_valid': ['pic3_', 'pic4_'],
    'X_test': ['pic5_', 'pic6_'],
    'y_train': ['label1_', 'label2_'],
    'y_valid': ['label3_', 'label4_'],
    'y_test': ['label5_', 'label6_']
}

dataset2 = {
    'X_train': ['train_a', 'train_b'],
    'X_valid': ['valid_a', 'valid_b'],
    'X_test': ['test_a', 'test_b'],
    'y_train': ['y_train_a', 'y_train_b'],
    'y_valid': ['y_valid_a', 'y_valid_b'],
    'y_test': ['y_test_a', 'y_test_b']
}

dataset3 = {
    'X_train': ['extra1_', 'extra2_'],
    'X_valid': ['extra3_', 'extra4_'],
    'X_test': ['extra5_', 'extra6_'],
    'y_train': ['ey1_', 'ey2_'],
    'y_valid': ['ey3_', 'ey4_'],
    'y_test': ['ey5_', 'ey6_']
}

data_list = [dataset1, dataset2, dataset3]

ARGS = {
    'data_list': data_list
}
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 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
bbox_crop Ran
ran on a synthesized input
Storife/RANet/codes/RANet_lib/RANet_lib.py
code served (permissive licence) · get_code("2d6d8d058d6ee1cf")
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 3, dtype family float, shape (2, 2, 2) 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)

# img is indexed as img[:, bbox[0]:bbox[2], bbox[1]:bbox[3]]
# This means img needs to be a tensor with at least 3 dimensions
# First dimension is batch (not sliced), remaining dimensions are spatial
# bbox is a sequence with at least 4 elements: [y_min, x_min, y_max, x_max]

img = torch.randn(2, 4, 3)  # batch=2, height=4, width=3
bbox = [1, 0, 3, 2]  # [y_min=1, x_min=0, y_max=3, x_max=2]

ARGS = {
    "img": img,
    "bbox": bbox,
}
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 3, dtype family float, shape (2, 2, 2) — shape (2, 2, 2) 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
Storife/RANet/codes/RANet_lib/RANet_resnet_ins.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, 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.

get_imagenet_model Ran
ran on a synthesized input
Storife/RANet/codes/RANet_lib/RANet_Model_imagenet.py
code served (permissive licence) · get_code("0d10f19c6657d0e0")
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 ResNet. 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
import torchvision.models as models

# Define a mock resnet_ins101 function since it's not a standard model
def resnet_ins101(pretrained=True):
    """Mock implementation of resnet_ins101"""
    model = models.resnet101(pretrained=pretrained)
    return model

# Make the function available in the models module namespace for the get_imagenet_model function
models.resnet_ins101 = resnet_ins101

# Set up the arguments
ARGS = {
    'type': 'resnet101',
    'pretrained': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
get_imagenet_model Ran
ran on a synthesized input
Storife/RANet/codes/RANet_lib/Resnet_ins101.py
code served (permissive licence) · get_code("1f5fe5bccb134719")
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 ResNet. 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 torchvision.models as models

torch.manual_seed(0)

# The function get_imagenet_model takes two parameters:
# 1. type: a string specifying the model type
# 2. pretrained: a boolean flag (defaults to True)

# Looking at the function body, it:
# - Takes a 'type' parameter (string)
# - Takes a 'pretrained' parameter (boolean, default True)
# - Calls models.__dict__[model_name](pretrained=pretrained)
# - Returns a model object

# We need to pick a valid model type that exists in torchvision.models
# Common valid types that exist: 'vgg16', 'resnet50', 'resnet101'
# The function has special handling for these

ARGS = {
    'type': 'resnet50',
    'pretrained': False  # Using False to avoid downloading pretrained weights
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
make_layer2 Ran
ran on a synthesized input
Storife/RANet/codes/RANet_model.py
code served (permissive licence) · get_code("ba18985adbbee7fd")
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 Sequential. 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 = {
    "input_feature": 16,
    "out_feature": 32,
    "up_scale": 1,
    "ksize": 3,
    "d": 1,
    "groups": 1
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make_layer2 Ran
ran on a synthesized input
v1viswan/RANet_modifications/codes/RANet_model.py
code served (permissive licence) · get_code("25478e593024c8f9")
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 Sequential. 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 = {
    'input_feature': 16,
    'out_feature': 32,
    'up_scale': 2,
    'ksize': 3,
    'd': 1,
    'groups': 1
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
msk2bbox Ran
ran on a synthesized input
Storife/RANet/codes/RANet_lib/RANet_lib.py
code served (permissive licence) · get_code("a3591e754555960f")
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 1, dtype family float, shape (4,) as a later run recorded it. 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, 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
import numpy as np

torch.manual_seed(0)

# Create a mask tensor with shape [1, 480, 864] (batch=1, height=480, width=864)
# The mask should have some non-zero values so the function processes it
msk = torch.zeros(1, 480, 864)
# Add some non-zero values in the middle region to create a valid bounding box
msk[0, 100:200, 200:400] = 1.0

ARGS = {
    "msk": msk,
    "k": 1.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 1, dtype family float, shape (4,) — shape (4,) 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
msk2bbox Ran
ran on a synthesized input
v1viswan/RANet_modifications/codes/RANet_lib/RANet_lib.py
code served (permissive licence) · get_code("2b58e4965c15d608")
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 1, dtype family float, shape (4,) as a later run recorded it. 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, 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
import numpy as np

torch.manual_seed(0)

# Create a valid mask tensor of shape 1xWxH with some non-zero values
# The function expects a 3D tensor where first dimension is 1
msk = torch.zeros(1, 480, 864)
# Add some non-zero values to create a region for bounding box calculation
msk[0, 100:200, 150:300] = 1.0

ARGS = {
    "msk": msk,
    "k": 1.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 1, dtype family float, shape (4,) — shape (4,) 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
nms_excitation Ran
ran on a synthesized input
v1viswan/RANet_modifications/codes/RANet_model.py
code served (permissive licence) · get_code("ce75ee8116383c03")
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 4, dtype family float, shape (2, 4, 3, 5) 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
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small score_map tensor with shape (batch_size, num_channels, height, width)
# Using distinct dimensions: batch=2, channels=4, height=3, width=5
score_map = torch.rand(2, 4, 3, 5)

# Define all parameters
ARGS = {
    'score_map': score_map,
    'excitation_score': 0.5,
    'threshold': 0.8,
    'window_size': 1
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
resnet_ins101 Ran
ran on a synthesized input
Storife/RANet/codes/RANet_lib/RANet_resnet_ins.py
code served (permissive licence) · get_code("ae58bcdbb1c048c0")
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 ResNet_ins. 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
import math

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet_ins — a ResNet_ins output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet_ins 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
checkpoint_load Not yet run
unverified (harvested, no recorded run)
Storife/RANet/codes/RANet_lib/RANet_lib.py
code served (permissive licence) · get_code("21179515d0388b55")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
conv3x3 686 other papers
143 dated earlier, 10 the same month, 533 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 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

Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restrict their practicality. Matching based and propagation based methods run at a faster speed by avoiding OL techniques. However, they are limited by sub-optimal accuracy, due to mismatching and drifting problems. In this paper, we develop a real-time yet very accurate Ranking Attention Network (RANet) for VOS. Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner. To better utilize the similarity maps, we propose a novel ranking attention module, which automatically ranks and selects these maps for fine-grained VOS performance. Experiments on DAVIS-16 and DAVIS-17 datasets show that our RANet achieves the best speed-accuracy trade-off, e.g., with 33 milliseconds per frame and J&F=85.5% on DAVIS-16. With OL, our RANet reaches J&F=87.1% on DAVIS-16, exceeding state-of-the-art VOS methods. The code can be found at https://github.com/Storife/RANet.

For agents

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

get_harvested_code_for_paper("1908.06647")
get_code_for_paper("1908.06647")
have("1908.06647")

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

curl https://syntology.ai/api/ran/1908.06647.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.06647.svg)](https://syntology.ai/paper/1908.06647)

Connect an agent — have() is free.