SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.02665 · 2019

Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 4 failures 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/1907.02665.json · badge: /api/ran/1907.02665.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
zwx8981/DBCNN-PyTorch canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
CovpoolLayer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zwx8981/DBCNN-PyTorch/MPNCOV.py
code served (permissive licence) · get_code("3e3d33392b6ecdd9")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 4) 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 CovpoolLayer takes a single parameter 'var' which should be a tensor
# Looking at the forward pass:
# - input is reshaped to (batchSize, dim, M) where M = h * w
# - So input should be a 4D tensor of shape (batchSize, dim, h, w)

# Create a small input tensor with distinct dimensions
# batch_size=2, dim=4, h=3, w=5
input_tensor = torch.randn(2, 4, 3, 5, dtype=torch.float32)

ARGS = {
    'var': input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 4, 4) — shape (2, 4, 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
SqrtmLayer Ran
ran; our contract draft was wrong, not the code
zwx8981/DBCNN-PyTorch/MPNCOV.py
pointer only (licence: MIT); the stored copy get_code serves, from GitZH-Chen/RiemGCP, is pointer only (licence: NONE) · get_code("3c7b6412a1bc9cf4")
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 GitZH-Chen/RiemGCP, 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.

TriuvecLayer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zwx8981/DBCNN-PyTorch/MPNCOV.py
code served (permissive licence) · get_code("5cee54d3483cad8f")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 10, 1) 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 TriuvecLayer takes a single parameter 'var' which should be a tensor
# Looking at the forward pass:
# - input is reshaped to (batchSize, dim * dim)
# - It extracts the upper triangular part
# - Returns shape (batchSize, dim * (dim + 1) / 2)
# So input should be a 3D tensor of shape (batchSize, dim, dim)

batchSize = 2
dim = 4

# Create a small input tensor with requires_grad=True for backward pass
input_tensor = torch.randn(batchSize, dim, dim, dtype=torch.float32, requires_grad=True)

ARGS = {
    'var': input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 10, 1) — shape (2, 10, 1) 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
default_loader Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zwx8981/DBCNN-PyTorch/BaseCNN.py
pointer only (licence: MIT); the stored copy get_code serves, from NA-HMC/NA-HMC, is pointer only (licence: NONE) · get_code("7bf07d5f59aae36d")
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 NA-HMC/NA-HMC, 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.

default_loader Ran
ran, honoured the contract we drafted
zwx8981/DBCNN-PyTorch/Koniq_10k.py
code served (permissive licence) · get_code("87435c3bde0423f0")
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 Image. 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 numpy as np
from PIL import Image
import io
import tempfile
import os

# Create a temporary test image file
temp_dir = tempfile.mkdtemp()
img = Image.new('RGB', (10, 10), color='red')
img_path = os.path.join(temp_dir, 'test_image.png')
img.save(img_path)

ARGS = {
    'path': img_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
getDistortionTypeFileName Ran
ran on a synthesized input
zwx8981/DBCNN-PyTorch/LIVEChallengeFolder.py
code served (permissive licence) · get_code("c7c109231d52f840")
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 list, ndim 1, 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 os.path

ARGS = {
    'path': '/tmp/test_images',
    'num': 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
getFileName Ran
ran on a synthesized input
zwx8981/DBCNN-PyTorch/Koniq_10k.py
code served (permissive licence) · get_code("21279e4b4f46e1ce")
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 list, ndim 1, 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 os
import tempfile
import shutil

# Create a temporary directory with test files
temp_dir = tempfile.mkdtemp()
test_files = [
    "file1.txt",
    "file2.txt",
    "document.pdf",
    "image.png",
    "data.csv",
    "script.py"
]

for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write("test content")

ARGS = {
    "path": temp_dir,
    "suffix": ".txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
getFileName Ran
ran on a synthesized input
zwx8981/DBCNN-PyTorch/LIVEFolder.py
code served (permissive licence) · get_code("ca6adfb82b2bf37e")
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 list, ndim 1, 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 os
import tempfile
import shutil

# Create a temporary directory with test files
temp_dir = tempfile.mkdtemp()

# Create some test files with different suffixes
test_files = [
    "file1.txt",
    "file2.txt",
    "document.pdf",
    "image.png",
    "data.csv",
    "script.py"
]

for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write("test content")

# Define arguments for getFileName
ARGS = {
    "path": temp_dir,
    "suffix": ".txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
pil_loader Ran
ran, honoured the contract we drafted
zwx8981/DBCNN-PyTorch/BaseCNN.py
code served (permissive licence) · get_code("f321f54723433661")
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) and returned Image. 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 numpy as np
from PIL import Image
import io
import os
import tempfile

# Create a temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Create a simple RGB image and save it to a temporary file
img = Image.new('RGB', (10, 10), color=(73, 109, 137))
test_image_path = os.path.join(temp_dir, 'test_image.jpg')
img.save(test_image_path)

ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
accimage_loader Not yet run
unverified (harvested, no recorded run)
zwx8981/DBCNN-PyTorch/BaseCNN.py
pointer only (licence: MIT); the stored copy get_code serves, from RobustBench/robustbench, is pointer only (licence: NOASSERTION) · get_code("404fb2b2daa1ae78")
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 RobustBench/robustbench, and GitHub could not classify the licence of that repository (NOASSERTION). 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 6 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
pil_loader 66 other papers
5 dated earlier, 61 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
and 63 more not named here
accimage_loader 39 other papers
3 dated earlier, 36 later
1702.00758 (2017-02)
HashNet: Deep Learning to Hash by Continuation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
and 36 more not named here
default_loader 28 other papers
28 later
2003.05033 (2020-03)
Generalized Energy Based Models
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
2004.11362 (2020-04)
Supervised Contrastive Learning
and 25 more not named here
CovpoolLayer 4 other papers
2 dated earlier, 2 later
1712.01034 (2017-12)
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
1904.06836 (2019-04)
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
2110.14381 (2021-10)
Temporal-attentive Covariance Pooling Networks for Video Recognition
and 1 more not named here
SqrtmLayer 4 other papers
2 dated earlier, 2 later
1712.01034 (2017-12)
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
1904.06836 (2019-04)
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
2110.14381 (2021-10)
Temporal-attentive Covariance Pooling Networks for Video Recognition
and 1 more not named here
TriuvecLayer 4 other papers
2 dated earlier, 2 later
1712.01034 (2017-12)
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
1904.06836 (2019-04)
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
2110.14381 (2021-10)
Temporal-attentive Covariance Pooling Networks for Video Recognition
and 1 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

We propose a deep bilinear model for blind image quality assessment (BIQA) that handles both synthetic and authentic distortions. Our model consists of two convolutional neural networks (CNN), each of which specializes in one distortion scenario. For synthetic distortions, we pre-train a CNN to classify image distortion type and level, where we enjoy large-scale training data. For authentic distortions, we adopt a pre-trained CNN for image classification. The features from the two CNNs are pooled bilinearly into a unified representation for final quality prediction. We then fine-tune the entire model on target subject-rated databases using a variant of stochastic gradient descent. Extensive experiments demonstrate that the proposed model achieves superior performance on both synthetic and authentic databases. Furthermore, we verify the generalizability of our method on the Waterloo Exploration Database using the group maximum differentiation competition.

For agents

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

get_harvested_code_for_paper("1907.02665")
get_code_for_paper("1907.02665")
have("1907.02665")

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

curl https://syntology.ai/api/ran/1907.02665.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.02665.svg)](https://syntology.ai/paper/1907.02665)

Connect an agent — have() is free.