SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.10904 · ECCV · 2022

AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection

Yipeng Gao, Wei-Shi Zheng, Lingxiao Yang, Yunmu Huang, Song Xie, Shiyong Li

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 (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 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/2209.10904.json · badge: /api/ran/2209.10904.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
Hlings/AcroFOD community
Papers with Code archive
5 ran · 2 no recorded run
FunctionStatusWhere it lives
_gaussian_map Ran
ran, honoured the contract we drafted
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("7829454dc92261cf")
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 ndarray, ndim 3, dtype family float, shape (60, 50, 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 numpy as np
import torch
import math

torch.manual_seed(0)

ARGS = {
    "height": 100,
    "width": 150,
    "x1": 10,
    "y1": 20,
    "x2": 60,
    "y2": 80,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (60, 50, 1) — shape (60, 50, 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
bbox_ioa Ran
ran, violated the contract we drafted
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("49f903f3a1e01747")
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 ndarray, ndim 1, dtype family float, shape (2,) 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 numpy as np

# box1 is a single bounding box with shape (4,) in format x1y1x2y2
box1 = np.array([10.0, 20.0, 30.0, 40.0])

# box2 is multiple bounding boxes with shape (n, 4) in format x1y1x2y2
box2 = np.array([
    [12.0, 22.0, 28.0, 38.0],
    [5.0, 15.0, 35.0, 45.0]
])

ARGS = {
    "box1": box1,
    "box2": box2,
    "eps": 1e-07
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
copy_paste Ran
ran, honoured the contract we drafted
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("f719dfb7693b1fbf")
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. 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 numpy as np
import torch
import cv2
import random

# Set seed for reproducibility
torch.manual_seed(0)
random.seed(0)

# Create two small dummy images
im1 = np.random.randint(0, 256, size=(100, 120, 3), dtype=np.uint8)
im2 = np.random.randint(0, 256, size=(100, 120, 3), dtype=np.uint8)

# Create labels with format: [class_id, xmin, ymin, xmax, ymax]
# labels1 has 2 objects of class 0 and 1 object of class 1
labels1 = np.array([
    [0, 10.0, 15.0, 40.0, 50.0],
    [0, 50.0, 20.0, 80.0, 60.0],
    [1, 85.0, 70.0, 110.0, 95.0]
], dtype=np.float32)

# labels2 has 2 objects of class 0 and 1 object of class 1
labels2 = np.array([
    [0, 20.0, 25.0, 50.0, 55.0],
    [0, 60.0, 30.0, 90.0, 70.0],
    [1, 88.0, 75.0, 115.0, 98.0]
], dtype=np.float32)

ARGS = {
    "im1": im1,
    "im2": im2,
    "labels1": labels1,
    "labels2": labels2,
    "p": 0.6
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, 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
get_bbox_ioa Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("63ffb24e0cb3ef24")
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 ndarray, ndim 1, dtype family float, shape (2,) 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 numpy as np

# Construct valid arguments for get_bbox_ioa

# box: a single bounding box in format x1y1x2y2
box = np.array([0.2, 0.3, 0.8, 0.9])

# labels_refine: array of labels where each row contains [label_id, x1, y1, x2, y2]
# This will be converted to list and have one element removed
labels_refine = np.array([
    [1, 0.1, 0.1, 0.5, 0.5],
    [2, 0.4, 0.4, 0.9, 0.9],
    [3, 0.6, 0.2, 0.95, 0.7]
])

# label_to_move: the label id to remove from the list
label_to_move = [2, 0.4, 0.4, 0.9, 0.9]

ARGS = {
    "box": box,
    "labels_refine": labels_refine,
    "label_to_move": label_to_move
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
xywh2xyxy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("294c11c540391122")
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 2, dtype family float, shape (2, 5) 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 numpy as np

torch.manual_seed(0)

# The function expects:
# x: array-like (torch.Tensor or numpy array) with shape (batch_size, 5)
#    where columns are [class, center_x, center_y, width, height]
# w: scalar (image width)
# h: scalar (image height)

# Create a small torch tensor with batch size 2 and 5 columns
x_torch = torch.randn(2, 5)

# Scalars for width and height
w = 640
h = 480

ARGS = {
    "x": x_torch,
    "w": w,
    "h": h
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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, 5) — shape (2, 5) 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
change_target Not yet run
unverified (harvested, no recorded run)
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("e9e88aa20d18e7a4")
How it ran

no invocation recorded.

copy_paste_api Not yet run
unverified (harvested, no recorded run)
Hlings/AcroFOD/utils/copy_paste_da.py
code served (permissive licence) · get_code("1d8d774d951cca01")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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

Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data. There exists two significant challenges: (1) Highly insufficient target domain data; (2) Potential over-adaptation and misleading caused by inappropriately amplified target samples without any restriction. To address these challenges, we propose an adaptive method consisting of two parts. First, we propose an adaptive optimization strategy to select augmented data similar to target samples rather than blindly increasing the amount. Specifically, we filter the augmented candidates which significantly deviate from the target feature distribution in the very beginning. Second, to further relieve the data limitation, we propose the multi-level domain-aware data augmentation to increase the diversity and rationality of augmented data, which exploits the crossimage foreground-background mixture. Experiments show that the proposed method achieves state-of-the-art performance on multiple benchmarks. The code is available at https://github.com/Hlings/AcroFOD.

For agents

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

get_harvested_code_for_paper("2209.10904")
get_code_for_paper("2209.10904")
have("2209.10904")

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

curl https://syntology.ai/api/ran/2209.10904.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.10904.svg)](https://syntology.ai/paper/2209.10904)

Connect an agent — have() is free.