SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.13123 · AAAI · 2022

Content-Variant Reference Image Quality Assessment via Knowledge Distillation

Wei Wang, Zehuan Yuan, Changhu Wang, Wei Ji, Chuchu Han, Guanghao Yin, Shouqian Sun

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 2 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/2202.13123.json · badge: /api/ran/2202.13123.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
guanghaoyin/CVRKD-IQA community
Papers with Code archive
5 ran · 2 no recorded run
FunctionStatusWhere it lives
Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("e58ef2d53828a3a5")
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, Bottleneck: the run constructed the object and did not call it, so no result was computed. 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)

# Create a downsample module that matches what the forward pass expects
# The downsample is called with x, so it should accept a tensor and return a tensor
downsample = nn.Sequential(
    nn.Conv2d(4, 16, kernel_size=1, stride=1, bias=False),
    nn.BatchNorm2d(16)
)

ARGS = {
    'inplanes': 4,
    'planes': 4,
    'stride': 1,
    'downsample': downsample
}
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 Bottleneck — 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 Bottleneck 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
MLPMixer Ran
ran on a synthesized input · constructed an object; no result was computed
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("f446b482ef5e6b9d")
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, MLPMixer: the run constructed the object and did not call it, so no result was computed. 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
from functools import partial
from einops.layers.torch import Rearrange, Reduce

torch.manual_seed(0)

ARGS = {
    'image_size': 8,
    'channels': 3,
    'patch_size': 2,
    'dim': 4,
    'depth': 2,
    'expansion_factor': 4,
    'dropout': 0.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MLPMixer — 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 MLPMixer 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
PreNormResidual Ran
ran on a synthesized input · constructed an object; no result was computed
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("6a8eace37d4431b3")
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, PreNormResidual: the run constructed the object and did not call it, so no result was computed. 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)

# Create a small function module that takes normalized input and returns output
class SimpleFunction(nn.Module):
    def __init__(self, dim_in, dim_out):
        super().__init__()
        self.linear = nn.Linear(dim_in, dim_out)
    
    def forward(self, x):
        return self.linear(x)

# Parameters for PreNormResidual
dim = 4
fn = SimpleFunction(dim_in=4, dim_out=4)

ARGS = {
    "dim": dim,
    "fn": fn
}
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 PreNormResidual — 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 PreNormResidual 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
RegressionFCNet Ran
ran on a synthesized input · constructed an object; no result was computed
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("0b313e4a4b70b3e9")
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, RegressionFCNet: the run constructed the object and did not call it, so no result was computed. 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 = {}
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 RegressionFCNet — 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 RegressionFCNet 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
ResNetBackbone Ran
ran on a synthesized input · constructed an object; no result was computed
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("ca90470574cf580c")
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, ResNetBackbone: the run constructed the object and did not call it, so no result was computed. 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)

class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.bn3(out)
        if self.downsample is not None:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out


ARGS = {
    'outc': 2048,
    'block': Bottleneck,
    'layers': [3, 4, 6, 3],
    '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 ResNetBackbone — 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 ResNetBackbone 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
DistillationIQANet Not yet run
unverified (harvested, no recorded run)
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("60384d9d170e21dc")
How it ran

no invocation recorded.

initialize_weights Not yet run
unverified (harvested, no recorded run)
guanghaoyin/CVRKD-IQA/models/DistillationIQA.py
code served (permissive licence) · get_code("2c8a0bc68cf9de69")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
Bottleneck
brick of this paper's assembly: model
8 other papers
6 dated earlier, 2 later · 7 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1607.01719 (2016-07)
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
2103.04337 (2021-03)
Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification
and 5 more not named here
PreNormResidual
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2401.02937 (2024-01)
Locally Adaptive Neural 3D Morphable Models

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

Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent no-reference (NR-IQA) methods have made great progress to predict image quality free from the reference image, they still have the potential to achieve better performance since HQ image information is not fully exploited. In contrast, full-reference (FR-IQA) methods tend to provide more reliable quality evaluation, but its practicability is affected by the requirement for pixel-level aligned reference images. To address this, we firstly propose the content-variant reference method via knowledge distillation (CVRKD-IQA). Specifically, we use non-aligned reference (NAR) images to introduce various prior distributions of high-quality images. The comparisons of distribution differences between HQ and LQ images can help our model better assess the image quality. Further, the knowledge distillation transfers more HQ-LQ distribution difference information from the FR-teacher to the NAR-student and stabilizing CVRKD-IQA performance. Moreover, to fully mine the local-global combined information, while achieving faster inference speed, our model directly processes multiple image patches from the input with the MLP-mixer. Cross-dataset experiments verify that our model can outperform all NAR/NR-IQA SOTAs, even reach comparable performance with FR-IQA methods on some occasions. Since the content-variant and non-aligned reference HQ images are easy to obtain, our model can support more IQA applications with its relative robustness to content variations. Our code and more detail elaborations of supplement are available: https://github.com/guanghaoyin/CVRKD-IQA. * This work was performed while Guanghao Yin worked as an intern at ByteDance. † Equal Contribution.

For agents

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

get_harvested_code_for_paper("2202.13123")
get_code_for_paper("2202.13123")
have("2202.13123")

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

curl https://syntology.ai/api/ran/2202.13123.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.13123.svg)](https://syntology.ai/paper/2202.13123)

Connect an agent — have() is free.