SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.09507 · ECCV · 2022

Towards Data-Efficient Detection Transformers

Dacheng Tao, Jing Zhang, Wen Wang, Yang Cao, Yongliang Shen

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 (1 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/2203.09507.json · badge: /api/ran/2203.09507.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
encounter1997/de-conddetr marked official in Papers with Code
Papers with Code archive
3 ran · 2 no recorded run
encounter1997/DE-DETRs community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
NestedTensor Ran
ran on a synthesized input · constructed an object; no result was computed
encounter1997/de-conddetr/models/conditional_detr.py
code served (permissive licence) · get_code("38eda343ff956bb1")
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, NestedTensor: 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 tensor (batch=2, dim=4)
tensors = torch.randn(2, 4)

# Create a mask tensor with the same batch size
mask = torch.ones(2, dtype=torch.bool)

# Define ARGS mapping all parameters to their values
ARGS = {
    'tensors': tensors,
    'mask': mask
}
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 NestedTensor — 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 NestedTensor 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_clones Ran
ran; our contract draft was wrong, not the code
encounter1997/de-conddetr/models/conditional_detr.py
code served (permissive licence) · get_code("78c715d857ace5c3")
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 ModuleList. 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 copy

torch.manual_seed(0)

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

# Construct the arguments
module = SimpleModule()
N = 5

ARGS = {
    'module': module,
    'N': N
}
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 ModuleList — a ModuleList output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModuleList output the recorded ndim 1 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
nested_tensor_from_tensor_list Ran
ran; our contract draft was wrong, not the code
encounter1997/de-conddetr/models/conditional_detr.py
code served (permissive licence) · get_code("4c8b2d763e2923a0")
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 NestedTensor. 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
from typing import List

torch.manual_seed(0)

# Create a list of 3D tensors with different sizes
# Each tensor has shape (C, H, W) where C=channels, H=height, W=width
tensor1 = torch.randn(3, 4, 5)  # 3 channels, 4 height, 5 width
tensor2 = torch.randn(3, 6, 7)  # 3 channels, 6 height, 7 width

tensor_list = [tensor1, tensor2]

ARGS = {
    "tensor_list": tensor_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NestedTensor — a NestedTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NestedTensor 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
nested_tensor_from_tensor_list Ran
ran; our contract draft was wrong, not the code
encounter1997/DE-DETRs/models/detr.py
code served (permissive licence) · get_code("1bf01bde72e96783")
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 NestedTensor. 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
from typing import List

torch.manual_seed(0)

# Create a list of 3D tensors with different shapes
# Each tensor has shape (C, H, W) where C=channels, H=height, W=width
tensor1 = torch.randn(3, 4, 5)  # 3 channels, 4 height, 5 width
tensor2 = torch.randn(3, 6, 7)  # 3 channels, 6 height, 7 width

tensor_list = [tensor1, tensor2]

ARGS = {
    "tensor_list": tensor_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NestedTensor — a NestedTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NestedTensor 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
ConditionalDETR Not yet run
unverified (harvested, no recorded run)
encounter1997/de-conddetr/models/conditional_detr.py
code served (permissive licence) · get_code("44ae34f47ab8abf3")
How it ran

no invocation recorded.

DETR Not yet run
unverified (harvested, no recorded run)
encounter1997/DE-DETRs/models/detr.py
code served (permissive licence) · get_code("ddccc349602c4998")
How it ran

no invocation recorded.

_onnx_nested_tensor_from_tensor_list Not yet run
unverified (harvested, no recorded run)
encounter1997/de-conddetr/models/conditional_detr.py
code served (permissive licence) · get_code("6be367607d25292a")
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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 4 later) and 3 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
nested_tensor_from_tensor_list
brick of this paper's assembly: helper
55 other papers
10 dated earlier, 3 the same month, 42 later · 17 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2101.01909 (2021-01)
Line Segment Detection Using Transformers without Edges
and 52 more not named here
_onnx_nested_tensor_from_tensor_list
brick of this paper's assembly: helper
24 other papers
6 dated earlier, 2 the same month, 16 later · 17 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.14167 (2021-03)
COTR: Correspondence Transformer for Matching Across Images
2104.07434 (2021-04)
Points as Queries: Weakly Semi-supervised Object Detection by Points
and 21 more not named here
nested_tensor_from_tensor_list
brick of this paper's assembly: helper
19 other papers
7 dated earlier, 3 the same month, 9 later · 11 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.05399 (2021-03)
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
and 16 more not named here
_get_clones
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2103.11161 (2021-03)
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
2207.13820 (2022-07)
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

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

Detection transformers have achieved competitive performance on the sample-rich COCO dataset. However, we show most of them suffer from significant performance drops on small-size datasets, like Cityscapes. In other words, the detection transformers are generally data-hungry. To tackle this problem, we empirically analyze the factors that affect data efficiency, through a step-by-step transition from a dataefficient RCNN variant to the representative DETR. The empirical results suggest that sparse feature sampling from local image areas holds the key. Based on this observation, we alleviate the data-hungry issue of existing detection transformers by simply alternating how key and value sequences are constructed in the cross-attention layer, with minimum modifications to the original models. Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency. Experiments show that our method can be readily applied to different detection transformers and improve their performance on both small-size and sample-rich datasets. Code will be made publicly available at https://github.com/encounter1997/DE-DETRs.

For agents

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

get_harvested_code_for_paper("2203.09507")
get_code_for_paper("2203.09507")
have("2203.09507")

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

curl https://syntology.ai/api/ran/2203.09507.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.09507.svg)](https://syntology.ai/paper/2203.09507)

Connect an agent — have() is free.