SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.17111 · CVPR · 2023

Hierarchical Fine-Grained Image Forgery Detection and Localization

Xiaoming Liu, Xiaohong Liu, Zhiyuan Ren, Xiao Guo, Iacopo Masi, Steven Grosz, Fu Sy, Pa Ma

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (9 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 2 failures of our instrument; 5 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/2303.17111.json · badge: /api/ran/2303.17111.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
chelsea234/hifi_ifdl marked official in Papers with Code
Papers with Code archive
13 ran · 5 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("7b178f825d37ad2c")
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, BasicBlock: 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)

BN_MOMENTUM = 0.01

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=False)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        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)
        if self.downsample is not None:
            residual = self.downsample(x)
        out = out + residual
        out = self.relu(out)
        return out

# Create a downsample module that matches the expected input/output shapes
downsample_module = nn.Sequential(
    nn.Conv2d(3, 4, kernel_size=1, stride=2, bias=False),
    nn.BatchNorm2d(4, momentum=BN_MOMENTUM)
)

ARGS = {
    'inplanes': 3,
    'planes': 4,
    'stride': 2,
    'downsample': downsample_module
}
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 BasicBlock — 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 BasicBlock 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
Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("e1e3fde5abbd1dba")
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)

BN_MOMENTUM = 0.01

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, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=False)
        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 = out + residual
        out = self.relu(out)
        return out

# Create a minimal downsample module that transforms input channels to output channels
downsample_module = nn.Sequential(
    nn.Conv2d(8, 32, kernel_size=1, stride=1, bias=False),
    nn.BatchNorm2d(32, momentum=BN_MOMENTUM)
)

ARGS = {
    'inplanes': 8,
    'planes': 8,
    'stride': 1,
    'downsample': downsample_module
}
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
BranchCLS Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("9b8d5c657020b3da")
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, BranchCLS: 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)

# Construct ARGS dict with all parameters for BranchCLS
ARGS = {
    'in_channels': 3,
    'output_channels': 5
}
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 BranchCLS — 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 BranchCLS 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
CatDepth Ran
ran on a synthesized input
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("0600f3020a10ac5f")
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 4, 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 torch.nn as nn

# CatDepth.__init__ has no parameters beyond self
INIT_ARGS = {}

# forward(self, x, y) takes two tensors and concatenates them along dim=1
# Using distinct shapes: x has 3 channels, y has 5 channels
# Batch size 2, spatial dimensions 4x6
x = torch.randn(2, 3, 4, 6)
y = torch.randn(2, 5, 4, 6)

ARGS = {
    'x': x,
    'y': y
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — 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)
Flatten Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("e1419c05ef8cd25e")
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, Flatten: 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)

class Flatten(nn.Module):
    def __init__(self):
        super(Flatten, self).__init__()

    def forward(self, x):
        return x.view(x.size(0), -1)

# Create a small test tensor with shape (batch_size=2, channels=4, height=3, width=5)
# This mimics a typical 4D tensor from a CNN layer
x = torch.randn(2, 4, 3, 5)

# The Flatten module only uses:
# - x.size(0) to get batch size
# - x.view() to reshape
# No __init__ parameters are needed for Flatten

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 Flatten — 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 Flatten 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
GaussianSmoothing Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("e68d2ed847dcdb77")
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, GaussianSmoothing: 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
import numbers

torch.manual_seed(0)

# Construct arguments for GaussianSmoothing
channels = 3
kernel_size = 5
sigma = 1.0
dim = 2

ARGS = {
    'channels': channels,
    'kernel_size': kernel_size,
    'sigma': sigma,
    'dim': dim
}
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 GaussianSmoothing — 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 GaussianSmoothing 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
HighResolutionModule Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("d856f64b0cf32633")
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, HighResolutionModule: 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)

# Define a minimal block class that HighResolutionModule expects
class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes, momentum=0.01)
        self.relu = nn.ReLU(inplace=False)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes, momentum=0.01)
        self.downsample = downsample
        self.stride = stride
    
    def forward(self, x):
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out

# Set up parameters for HighResolutionModule
num_branches = 2
blocks = BasicBlock
num_blocks = [1, 1]  # 1 block per branch
num_inchannels = [16, 32]  # Input channels for each branch
num_channels = [16, 32]  # Output channels for each branch
fuse_method = 'sum'
multi_scale_output = True

ARGS = {
    'num_branches': num_branches,
    'blocks': blocks,
    'num_blocks': num_blocks,
    'num_inchannels': num_inchannels,
    'num_channels': num_channels,
    'fuse_method': fuse_method,
    'multi_scale_output': multi_scale_output
}
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 HighResolutionModule — 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 HighResolutionModule 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
IsolatingLossFunction Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("4ba5a22538ab5b90")
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, IsolatingLossFunction: 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

torch.manual_seed(0)

# Define center point and radius as tensors
c = torch.randn(4, requires_grad=False)  # feature dimension 4
R = torch.tensor(1.0, requires_grad=False)  # scalar radius

# Create ARGS dictionary with all required parameters
ARGS = {
    'c': c,
    'R': R,
    'p': 2,
    'threshold_val': 1.85
}
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 IsolatingLossFunction — 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 IsolatingLossFunction 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
LaPlacianMs Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("8fdceb4ff7b0075d")
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, LaPlacianMs: 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
import numbers

torch.manual_seed(0)

ARGS = {
    'in_c': 3,
    'gauss_ker_size': 3,
    'scale': [2],
    'drop_rate': 0.2
}
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 LaPlacianMs — 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 LaPlacianMs 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
PartialConv Ran
ran on a synthesized input · constructed an object; no result was computed
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("a0d87098e844ddaa")
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, PartialConv: 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)

ARGS = {
    'in_channels': 3,
    'out_channels': 4,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'dilation': 1,
    'groups': 1,
    'bias': True,
}
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 PartialConv — 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 PartialConv 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_cfg_defaults Ran
ran on a synthesized input
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("15843f1133de84f5")
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 CfgNode. 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 yacs.config import CfgNode as CN

torch.manual_seed(0)

# Initialize HRNET as a CfgNode with some default settings
HRNET = CN()
HRNET.MODEL = CN()
HRNET.MODEL.NAME = "hrnet"
HRNET.MODEL.PRETRAINED = False
HRNET.TRAIN = CN()
HRNET.TRAIN.LR = 0.001
HRNET.TRAIN.EPOCHS = 100
HRNET.TEST = CN()
HRNET.TEST.BATCH_SIZE = 32

# Since get_cfg_defaults() takes no parameters, ARGS should be an empty dict
ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
load_center_radius_api Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("eaead4d829ddf732")
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 tuple. 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 os
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory to serve as center_radius_dir
temp_dir = tempfile.mkdtemp()
center_radius_subdir = os.path.join(temp_dir, 'center')
os.makedirs(center_radius_subdir, exist_ok=True)

# Create small tensors for center and radius
center = torch.randn(4, 3)
radius = torch.randn(2)

# Save them to the expected path
save_dict = {'center': center, 'radius': radius}
radius_center_path = os.path.join(center_radius_subdir, 'radius_center.pth')
torch.save(save_dict, radius_center_path)

# Define ARGS
ARGS = {
    'center_radius_dir': center_radius_subdir
}
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 tuple — a tuple output has no array shape of its own; none is 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
weights_init Ran
ran; our contract draft was wrong, not the code
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("e9036b6dc10ccc06")
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 function. 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)

# The function weights_init takes one parameter: init_type
# It returns an initialization function that can be applied to nn.Module instances
# We need to provide a valid init_type string

# Valid init_type values based on the function body:
# 'gaussian', 'xavier', 'kaiming', 'orthogonal', 'default'

ARGS = {
    'init_type': 'gaussian'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
HiFi_Net Not yet run
unverified (harvested, no recorded run)
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("e7ef253ae9fcb7da")
How it ran

no invocation recorded.

HighResolutionNet Not yet run
unverified (harvested, no recorded run)
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("2b378f9963d3fa84")
How it ran

no invocation recorded.

NLCDetection Not yet run
unverified (harvested, no recorded run)
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("cb1672e1db145750")
How it ran

no invocation recorded.

NonLocalMask Not yet run
unverified (harvested, no recorded run)
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("a5749e5ab8a1fe26")
How it ran

no invocation recorded.

get_seg_model Not yet run
unverified (harvested, no recorded run)
chelsea234/hifi_ifdl/HiFi_Net.py
code served (permissive licence) · get_code("4020f7c8f5a456b0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 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 16 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
weights_init
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 1 later, 1 same year, order not determinable
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1712.02478 (2017-12)
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
and 5 more not named here
Flatten
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 2 only as an assembly brick
1312.5602 (2013-12)
Playing Atari with Deep Reinforcement Learning
1703.03400 (2017-03)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
2504.02199 (2025-04)
ESC: Erasing Space Concept for Knowledge Deletion

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

Differences in forgery attributes of images generated in CNN-synthesized and image-editing domains are large, and such differences make a unified image forgery detection and localization (IFDL) challenging. To this end, we present a hierarchical fine-grained formulation for IFDL representation learning. Specifically, we first represent forgery attributes of a manipulated image with multiple labels at different levels. Then we perform fine-grained classification at these levels using the hierarchical dependency between them. As a result, the algorithm is encouraged to learn both comprehensive features and inherent hierarchical nature of different forgery attributes, thereby improving the IFDL representation. Our proposed IFDL framework contains three components: multi-branch feature extractor, localization and classification modules. Each branch of the feature extractor learns to classify forgery attributes at one level, while localization and classification modules segment the pixel-level forgery region and detect imagelevel forgery, respectively. Lastly, we construct a hierarchical fine-grained dataset to facilitate our study. We demonstrate the effectiveness of our method on 7 different benchmarks, for both tasks of IFDL and forgery attribute classification. Our source code and dataset can be found: github.com/CHELSEA234/HiFi-IFDL.

For agents

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

get_harvested_code_for_paper("2303.17111")
get_code_for_paper("2303.17111")
have("2303.17111")

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

curl https://syntology.ai/api/ran/2303.17111.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.17111.svg)](https://syntology.ai/paper/2303.17111)

Connect an agent — have() is free.