SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.04448 · 2022

Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 5 failures of our instrument; 0 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/2207.04448.json · badge: /api/ran/2207.04448.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
yanglei18/mix-teaching canonical (classifier label)
classifier basis not recorded on the link
10 ran · 0 no recorded run
FunctionStatusWhere it lives
affine_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yanglei18/mix-teaching/MonoFlex/model/heatmap_coder.py
code served (permissive licence) · get_code("65a16c264996059d")
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 ndarray, ndim 2, dtype family float, shape (3, 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

# Create a small point array (multiple points)
point = np.array([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]])

# Create a 3x3 affine transformation matrix
# For 2D points extended to homogeneous coordinates (x, y, 1),
# we need a 3x3 matrix that will be transposed before matrix multiplication
matrix = np.array([
    [1.0, 0.0, 0.5],
    [0.0, 1.0, 0.3],
    [0.0, 0.0, 1.0]
])

ARGS = {
    "point": point,
    "matrix": matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (3, 2) — shape (3, 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
area Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yanglei18/mix-teaching/pseudo_labeling_tools/kitti_common.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from datongjie/bevspread, is pointer only (licence: NONE) · get_code("b156b7f755eebeae")
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 datongjie/bevspread, 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.

cat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yanglei18/mix-teaching/MonoFlex/model/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xinyulyu/fgpl, is pointer only (licence: NONE) · get_code("6cbf46794989b731")
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 xinyulyu/fgpl, 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.

compute_box_3d_image Ran
ran on a synthesized input
yanglei18/mix-teaching/pseudo_labeling_tools/kitti_common.py
code served (permissive licence) · get_code("2b9c60f8f974b4a0")
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 ndarray, ndim 2, dtype family float, shape (8, 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 arguments for compute_box_3d_image
# P: projection matrix (3x4)
# ry: rotation angle in radians (scalar)
# dims: [length, height, width] (3-element array/list)
# locs: [x, y, z] location (3-element array/list)

P = np.array([
    [500, 0, 320, 0],
    [0, 500, 240, 0],
    [0, 0, 1, 0]
], dtype=np.float32)

ry = 0.5  # rotation angle in radians

dims = np.array([2.0, 1.5, 1.2], dtype=np.float32)  # length, height, width

locs = np.array([10.0, 5.0, 30.0], dtype=np.float32)  # x, y, z coordinates

ARGS = {
    "P": P,
    "ry": ry,
    "dims": dims,
    "locs": locs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (8, 2) — shape (8, 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
convertRot2Alpha Ran
ran on a synthesized input
yanglei18/mix-teaching/pseudo_labeling_tools/create_data.py
code served (permissive licence) · get_code("5b20061e536cb233")
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 float, 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 math
import torch

torch.manual_seed(0)

# The function takes three scalar parameters: ry3d, z3d, x3d
# It performs arithmetic operations and comparisons on them
# All parameters should be numeric values

ARGS = {
    "ry3d": 1.5,
    "z3d": 2.0,
    "x3d": 0.5
}
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 float, 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
draw_box_3d Ran
ran on a synthesized input
yanglei18/mix-teaching/pseudo_labeling_tools/kitti_common.py
code served (permissive licence) · get_code("b000fc5a4c3fcea5")
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 ndarray, ndim 3, dtype family int, shape (100, 100, 3) 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 cv2

# Create a small image (100x100, 3 channels for BGR)
image = np.ones((100, 100, 3), dtype=np.uint8) * 255

# Create 8 3D corners (vertices of a 3D bounding box)
# These represent the 8 corners of a 3D box projected to 2D image space
# Shape: (8, 2) - 8 corners, each with (x, y) coordinates
corners = np.array([
    [10, 10],   # corner 0
    [30, 10],   # corner 1
    [30, 30],   # corner 2
    [10, 30],   # corner 3
    [20, 20],   # corner 4
    [40, 20],   # corner 5
    [40, 40],   # corner 6
    [20, 40],   # corner 7
], dtype=np.float32)

# Color for the box (BGR format: green)
color = (0, 255, 0)

ARGS = {
    "image": image,
    "corners": corners,
    "c": color,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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 int, shape (100, 100, 3) — shape (100, 100, 3) 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
encode_bbox Ran
ran on a synthesized input
yanglei18/mix-teaching/pseudo_labeling_tools/create_data.py
code served (permissive licence) · get_code("b0561e910c6ca9d8")
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 ndarray, ndim 1, dtype family float, shape (4,) 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

# Define arguments for encode_bbox function
P = np.array([
    [500.0, 0.0, 320.0, 0.0],
    [0.0, 500.0, 240.0, 0.0],
    [0.0, 0.0, 1.0, 0.0]
], dtype=np.float32)

ry = np.float32(0.5)  # rotation angle in radians

dims = np.array([1.5, 2.0, 4.0], dtype=np.float32)  # [length, height, width]

locs = np.array([10.0, 1.5, 30.0], dtype=np.float32)  # [x, y, z] location in 3D space

img_shape = (480, 640)  # (height, width)

ARGS = {
    'P': P,
    'ry': ry,
    'dims': dims,
    'locs': locs,
    'img_shape': img_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 (4,) — shape (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
gaussian_radius Ran
ran, honoured the contract we drafted
yanglei18/mix-teaching/MonoFlex/model/heatmap_coder.py
code served (permissive licence) · get_code("c044d44b5a7087e4")
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 float64, ndim 0, 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 numpy as np

# This function computes a gaussian radius given height and width
# It takes three numeric parameters: height, width, and min_overlap (with default 0.7)

ARGS = {
    "height": 32,
    "width": 64,
    "min_overlap": 0.7
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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_transfrom_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yanglei18/mix-teaching/MonoFlex/model/heatmap_coder.py
code served (permissive licence) · get_code("194052ec40659a42")
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 ndarray, ndim 2, dtype family float, shape (3, 3) 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

# Create small example inputs
center = np.array([100.0, 120.0], dtype=np.float32)
scale = np.array([50.0, 60.0], dtype=np.float32)
center_scale = [center, scale]

output_size = (64, 48)

ARGS = {
    "center_scale": center_scale,
    "output_size": output_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 3) 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
strip_prefix_if_present Ran
ran; our contract draft was wrong, not the code
yanglei18/mix-teaching/MonoFlex/utils/model_serialization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from BIT-DA/SDCA, is pointer only (licence: NONE) · get_code("5a951495ac113177")
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 BIT-DA/SDCA, 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.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 6 later) and 4 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
cat 18 other papers
12 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable · 3 only as an assembly brick
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
and 15 more not named here
strip_prefix_if_present 14 other papers
5 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2105.05013 (2021-05)
Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
and 11 more not named here
affine_transform 5 other papers
2 dated earlier, 1 the same month, 2 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2206.07372 (2022-06)
MonoGround: Detecting Monocular 3D Objects from the Ground
2207.10047 (2022-07)
Densely Constrained Depth Estimator for Monocular 3D Object Detection
and 2 more not named here
gaussian_radius 5 other papers
2 dated earlier, 1 the same month, 2 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2206.07372 (2022-06)
MonoGround: Detecting Monocular 3D Objects from the Ground
2207.10047 (2022-07)
Densely Constrained Depth Estimator for Monocular 3D Object Detection
and 2 more not named here
get_transfrom_matrix 5 other papers
2 dated earlier, 1 the same month, 2 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2206.07372 (2022-06)
MonoGround: Detecting Monocular 3D Objects from the Ground
2207.10047 (2022-07)
Densely Constrained Depth Estimator for Monocular 3D Object Detection
and 2 more not named here
area 2 other papers
2 later
2303.08498 (2023-03)
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection
2406.08785 (2024-06)
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D 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

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human annotations, we propose Mix-Teaching, an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching first generates pseudo-labels for unlabeled images by self-training. The student model is then trained on the mixed images possessing much more intensive and precise labeling by merging instance-level image patches into empty backgrounds or labeled images. This is the first to break the image-level limitation and put high-quality pseudo labels from multi frames into one image for semi-supervised training. Besides, as a result of the misalignment between confidence score and localization quality, it's hard to discriminate high-quality pseudo-labels from noisy predictions using only confidence-based criterion. To that end, we further introduce an uncertainty-based filter to help select reliable pseudo boxes for the above mixing operation. To the best of our knowledge, this is the first unified SSL framework for monocular 3D object detection. Mix-Teaching consistently improves MonoFlex and GUPNet by significant margins under various labeling ratios on KITTI dataset. For example, our method achieves around +6.34% AP@0.7 improvement against the GUPNet baseline on validation set when using only 10% labeled data. Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4.65% improvement on AP@0.7 for car detection, reaching 18.54% AP@0.7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard. The code and pretrained models will be released at https://github.com/yanglei18/Mix-Teaching.

For agents

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

get_harvested_code_for_paper("2207.04448")
get_code_for_paper("2207.04448")
have("2207.04448")

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

curl https://syntology.ai/api/ran/2207.04448.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.04448.svg)](https://syntology.ai/paper/2207.04448)

Connect an agent — have() is free.