SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.07532 · 2023

Referring Camouflaged Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 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 3 have no contract verdict; 1 failure 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/2306.07532.json · badge: /api/ran/2306.07532.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
zhangxuying1004/refcod canonical (classifier label)
classifier basis: census
4 ran · 5 no recorded run
FunctionStatusWhere it lives
count_total_parameters Ran
ran on a synthesized input
zhangxuying1004/refcod/utils/attri_tools/num_ops_params/flops_of_ops.py
code served (permissive licence) · get_code("74b68775f9fa72b1")
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 int, ndim 0, dtype family int, shape () 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
from torch import nn

torch.manual_seed(0)

# Build a small model with multiple parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        self.conv = nn.Conv1d(2, 5, kernel_size=3)
    
    def forward(self, x):
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 int, ndim 0, dtype family int, shape () — shape () 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
load_model_params Ran
ran on a synthesized input
zhangxuying1004/refcod/utils/utils.py
code served (permissive licence) · get_code("18a5802b4cf036f2")
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 SimpleModel. 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 os
import torch
import torch.nn as nn
import tempfile

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel()

# Create a temporary checkpoint file
with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.pt') as f:
    checkpoint_path = f.name

# Save a checkpoint with state_dict
checkpoint = {
    'state_dict': model.state_dict()
}
torch.save(checkpoint, checkpoint_path)

ARGS = {
    'model': model,
    'params_path': checkpoint_path
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
structure_loss Ran
ran; our contract draft was wrong, not the code
zhangxuying1004/refcod/utils/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vishal3477/Proactive-Object-Detection, is pointer only (licence: NONE) · get_code("90e63798570644f8")
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 vishal3477/Proactive-Object-Detection, 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.

to_cuda Ran
ran on a synthesized input
zhangxuying1004/refcod/utils/attri_tools/misc.py
code served (permissive licence) · get_code("42f8eb9b3a5e7002")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 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

torch.manual_seed(0)

# Test case 1: Single tensor
tensor_input = torch.randn(2, 4)

# Test case 2: List of tensors
list_input = [torch.randn(2, 4), torch.randn(3, 5)]

# Test case 3: Tuple of tensors
tuple_input = (torch.randn(2, 4), torch.randn(3, 5))

# Test case 4: Dict with tensor values
dict_input = {
    "a": torch.randn(2, 4),
    "b": torch.randn(3, 5),
    "nested": {
        "c": torch.randn(2, 3)
    }
}

# Test case 5: Nested structure with lists, tuples, and dicts
nested_input = [
    torch.randn(2, 4),
    (torch.randn(3, 5), torch.randn(2, 3)),
    {"x": torch.randn(4, 2), "y": [torch.randn(2, 1)]}
]

# The function takes a single parameter 'data'
ARGS = {
    "data": tensor_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
cal_macs_params Not yet run
unverified (harvested, no recorded run)
zhangxuying1004/refcod/utils/attri_tools/num_ops_params/num_ops_params_counter.py
code served (permissive licence) · get_code("37f1a36e810b4ad1")
How it ran

no invocation recorded.

cal_macs_params_v2 Not yet run
unverified (harvested, no recorded run)
zhangxuying1004/refcod/utils/attri_tools/num_ops_params/num_ops_params_counter.py
code served (permissive licence) · get_code("2ec8a7e793597bc6")
How it ran

no invocation recorded.

count_upsample Not yet run
unverified (harvested, no recorded run)
zhangxuying1004/refcod/utils/attri_tools/num_ops_params/flops_of_ops.py
code served (permissive licence) · get_code("cf409a870622cf7f")
How it ran

no invocation recorded.

profile Not yet run
unverified (harvested, no recorded run)
zhangxuying1004/refcod/utils/attri_tools/num_ops_params/count_info.py
code served (permissive licence) · get_code("65343c875e6ccbf2")
How it ran

no invocation recorded.

profile_with_inter_params Not yet run
unverified (harvested, no recorded run)
zhangxuying1004/refcod/utils/attri_tools/num_ops_params/count_info.py
code served (permissive licence) · get_code("2a5afe783683bcaf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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
structure_loss 6 other papers
3 dated earlier, 3 later
2106.06716 (2021-06)
DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation
2108.03990 (2021-08)
TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
2207.13362 (2022-07)
Camouflaged Object Detection via Context-aware Cross-level Fusion
and 3 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 consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scale dataset, called R2C7K, which consists of 7K images covering 64 object categories in real-world scenarios. Then, we develop a simple but strong dual-branch framework, dubbed R2CNet, with a reference branch embedding the common representations of target objects from referring images and a segmentation branch identifying and segmenting camouflaged objects under the guidance of the common representations. In particular, we design a Referring Mask Generation module to generate pixel-level prior mask and a Referring Feature Enrichment module to enhance the capability of identifying specified camouflaged objects. Extensive experiments show the superiority of our Ref-COD methods over their COD counterparts in segmenting specified camouflaged objects and identifying the main body of target objects. Our code and dataset are publicly available at https://github.com/zhangxuying1004/RefCOD.

For agents

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

get_harvested_code_for_paper("2306.07532")
get_code_for_paper("2306.07532")
have("2306.07532")

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

curl https://syntology.ai/api/ran/2306.07532.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.07532.svg)](https://syntology.ai/paper/2306.07532)

Connect an agent — have() is free.