SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.02541 · ECCV · 2022

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

Zeming Li, Jian Sun, Songtao Liu, Weixin Mao, Zheng Ge, Hongyu Zhou, Haiyan Yu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 2 have no contract verdict; 0 failures of our instrument; 1 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/2207.02541.json · badge: /api/ran/2207.02541.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
Megvii-BaseDetection/DenseTeacher canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
QFLv2 Ran
ran on a synthesized input
Megvii-BaseDetection/DenseTeacher/coco-full-LSJ/runner.py
code served (permissive licence) · get_code("c659281f12b19994")
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 0, dtype family float, 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create tiny tensors for the QFLv2 function
batch_size = 2
num_classes = 4

# pred_sigmoid: predictions after sigmoid, shape (batch_size, num_classes)
pred_sigmoid = torch.sigmoid(torch.randn(batch_size, num_classes))

# teacher_sigmoid: teacher predictions after sigmoid, same shape
teacher_sigmoid = torch.sigmoid(torch.randn(batch_size, num_classes))

# weight: importance weights for each sample
# Should have same shape as pred_sigmoid
# Values: > 0 for positive samples, == 0 for negative samples, < 0 for ignore
weight = torch.tensor([
    [1.0, 1.0, 0.0, -1.0],
    [1.0, 0.0, 0.0, 1.0]
], dtype=torch.float32)

# beta parameter
beta = 2.0

# reduction parameter
reduction = 'mean'

ARGS = {
    'pred_sigmoid': pred_sigmoid,
    'teacher_sigmoid': teacher_sigmoid,
    'weight': weight,
    'beta': beta,
    'reduction': reduction
}
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 0, dtype family float, 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
compute_ious Ran
ran on a synthesized input
Megvii-BaseDetection/DenseTeacher/coco-full-LSJ/fcos.py
code served (permissive licence) · get_code("2a5f1d7086f6062f")
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, ndim 2, 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

torch.manual_seed(0)

# Create two small tensors with shape (2, 4) representing bounding boxes
# in FCOS format (l, t, r, b) - left, top, right, bottom
pred = torch.tensor([
    [1.0, 2.0, 3.0, 4.0],
    [0.5, 1.5, 2.5, 3.5]
], dtype=torch.float32)

target = torch.tensor([
    [1.2, 2.1, 3.2, 4.1],
    [0.6, 1.6, 2.6, 3.6]
], dtype=torch.float32)

ARGS = {
    "pred": pred,
    "target": target
}
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, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
is_parallel Not yet run
unverified (harvested, no recorded run)
Megvii-BaseDetection/DenseTeacher/coco-full-LSJ/ema.py
code served (permissive licence) · get_code("bbbb5d6a28074b9d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 2 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
is_parallel 8 other papers
1 dated earlier, 7 later
1803.11365 (2018-03)
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
2209.10248 (2022-09)
BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo
2211.09445 (2022-11)
aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception
and 5 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

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any postprocessing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods. Code is available at https://github.com/Megvii-BaseDetection/DenseTeacher

For agents

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

get_harvested_code_for_paper("2207.02541")
get_code_for_paper("2207.02541")
have("2207.02541")

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

curl https://syntology.ai/api/ran/2207.02541.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.02541.svg)](https://syntology.ai/paper/2207.02541)

Connect an agent — have() is free.