SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.13362 · 2022

Camouflaged Object Detection via Context-aware Cross-level Fusion

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 1 has no contract verdict; 3 failures of our instrument; 3 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/2207.13362.json · badge: /api/ran/2207.13362.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
thograce/C2FNet canonical (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
thograce/C2FNet/lib/ResNet.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.

cus_sample Ran
ran on a synthesized input
thograce/C2FNet/utils/tensor_ops.py
code served (permissive licence) · get_code("e4e504ef2f934a74")
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, 16, 16) 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.functional as F

torch.manual_seed(0)

# Create a small input tensor for interpolation
# Shape: (batch=2, channels=4, height=8, width=8)
feat = torch.randn(2, 4, 8, 8)

# Define ARGS with two possible configurations
# We'll use the 'size' parameter option
ARGS = {
    'feat': feat,
    'size': (16, 16)  # Target output spatial dimensions
}

# Alternative configuration using 'scale_factor' would be:
# ARGS = {
#     'feat': feat,
#     'scale_factor': 2.0
# }
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, 16, 16) — shape (2, 4, 16, 16) 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
get_loader Ran
ran; our contract draft was wrong, not the code
thograce/C2FNet/utils/dataloader.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from CSYSI/DPU-Former, is pointer only (licence: NONE) · get_code("e04135543eeb06ab")
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 CSYSI/DPU-Former, 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.

structure_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thograce/C2FNet/MyTrain.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liuzywen/tritransnet, is pointer only (licence: NONE) · get_code("797eafbb72dabcfd")
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 liuzywen/tritransnet, 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.

res2net101_v1b Not yet run
unverified (harvested, no recorded run)
thograce/C2FNet/lib/Res2Net_v1b.py
code served (permissive licence) · get_code("e970716f1c7c523e")
How it ran

no invocation recorded.

res2net50_v1b Not yet run
unverified (harvested, no recorded run)
thograce/C2FNet/lib/Res2Net_v1b.py
code served (permissive licence) · get_code("10fe097f4b54b650")
How it ran

no invocation recorded.

res2net50_v1b_26w_4s Not yet run
unverified (harvested, no recorded run)
thograce/C2FNet/lib/Res2Net_v1b.py
code served (permissive licence) · get_code("968a61f3b3fb56f7")
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, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 5 later) and 1 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
398 dated earlier, 7 the same month, 270 later, 11 same year, order not determinable · 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
res2net101_v1b 8 other papers
3 dated earlier, 5 later
2107.02368 (2021-07)
UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation
2108.08162 (2021-08)
Specificity-preserving RGB-D Saliency Detection
2203.14291 (2022-03)
Video Polyp Segmentation: A Deep Learning Perspective
and 5 more not named here
res2net50_v1b 6 other papers
2 dated earlier, 4 later
2107.02368 (2021-07)
UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation
2203.14291 (2022-03)
Video Polyp Segmentation: A Deep Learning Perspective
2308.03166 (2023-08)
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
and 3 more not named here
structure_loss 6 other papers
2 dated earlier, 4 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
2306.07532 (2023-06)
Referring Camouflaged Object Detection
and 3 more not named here
get_loader 1 other paper
1 later
2506.21866 (2025-06)
Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images
res2net50_v1b_26w_4s 1 other paper
1 dated earlier
2105.12555 (2021-05)
Context-aware Cross-level Fusion Network for Camouflaged Object Detection

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

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://github.com/Ben57882/C2FNet-TSCVT.

For agents

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

get_harvested_code_for_paper("2207.13362")
get_code_for_paper("2207.13362")
have("2207.13362")

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

curl https://syntology.ai/api/ran/2207.13362.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.13362.svg)](https://syntology.ai/paper/2207.13362)

Connect an agent — have() is free.