SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.09124 · 2019

SeesawFaceNets: sparse and robust face verification model for mobile platform

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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; 3 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 6 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/1908.09124.json · badge: /api/ran/1908.09124.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
cvtower/seesawfacenet_pytorch community (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
pshashk/seesaw-facenet reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
cvtower/SeesawNet_pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Block Ran
ran; our contract draft was wrong, not the code
pshashk/seesaw-facenet/model.py
pointer only (licence: NONE) · get_code("41b5161a608d5f29")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pshashk/seesaw-facenet 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.

Conv Ran
ran; our contract draft was wrong, not the code
pshashk/seesaw-facenet/model.py
pointer only (licence: NONE) · get_code("b71052fb86154367")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pshashk/seesaw-facenet 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.

calibrate_box Ran
ran on a synthesized input
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/box_utils.py
code served (permissive licence) · get_code("6b0e6100d2ca104e")
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 (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 numpy as np

# Create sample bounding boxes with shape [n, 5]
# Format: [x1, y1, x2, y2, score]
n = 2
bboxes = np.array([
    [10.0, 20.0, 50.0, 80.0, 0.9],
    [15.0, 25.0, 60.0, 90.0, 0.85]
], dtype=np.float32)

# Create sample offsets with shape [n, 4]
# These are adjustment factors for the bounding box coordinates
offsets = np.array([
    [0.01, 0.02, -0.01, 0.03],
    [0.02, -0.01, 0.01, 0.02]
], dtype=np.float32)

ARGS = {
    "bboxes": bboxes,
    "offsets": offsets
}
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 (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
conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
cvtower/SeesawNet_pytorch/code/models/imagenet/seesaw.py
pointer only (licence: NONE) · get_code("0db9f814cdec6488")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvtower/SeesawNet_pytorch 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.

conv_bn Ran
ran; our contract draft was wrong, not the code
cvtower/SeesawNet_pytorch/code/models/imagenet/seesaw.py
pointer only (licence: NONE) · get_code("80d427a5f4557b3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvtower/SeesawNet_pytorch 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.

convert_to_square Ran
ran on a synthesized input
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/box_utils.py
code served (permissive licence) · get_code("c4e1ca09fcca76fc")
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 (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 numpy as np

# Create a small array of bounding boxes with shape [n, 5]
# n=2 bounding boxes, 5 columns: [x1, y1, x2, y2, confidence]
bboxes = np.array([
    [10.0, 20.0, 50.0, 70.0, 0.9],
    [100.0, 150.0, 200.0, 250.0, 0.8]
], dtype=np.float32)

ARGS = {
    "bboxes": bboxes
}
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 (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
findNonreflectiveSimilarity Ran
ran, honoured the contract we drafted
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/matlab_cp2tform.py
code served (permissive licence) · get_code("d074710facc3ca20")
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 3, 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

np.random.seed(0)

# Create sample point correspondence data
# uv: source points (2D coordinates)
# xy: target points (2D coordinates)
# We need at least 2 unique points for the transformation to be well-defined
# The function expects M points with 2 coordinates each

uv = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [1.0, 1.0],
    [0.0, 1.0]
], dtype=np.float64)

xy = np.array([
    [1.0, 1.0],
    [2.0, 1.5],
    [1.5, 2.5],
    [0.5, 2.0]
], dtype=np.float64)

options = {'K': 2}

ARGS = {
    'uv': uv,
    'xy': xy,
    'options': options
}
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 tuple, ndim 3, 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
get_affine_transform_matrix Ran
ran, honoured the contract we drafted
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/align_trans.py
code served (permissive licence) · get_code("b7f364dbce963974")
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 (2, 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 source points (4 points with x, y coordinates)
src_pts = np.array([
    [10.0, 20.0],
    [30.0, 40.0],
    [50.0, 60.0],
    [70.0, 80.0]
], dtype=np.float32)

# Create destination points (4 points with x, y coordinates)
# These represent where the source points should map to
dst_pts = np.array([
    [15.0, 25.0],
    [35.0, 45.0],
    [55.0, 65.0],
    [75.0, 85.0]
], dtype=np.float32)

ARGS = {
    'src_pts': src_pts,
    'dst_pts': dst_pts
}
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 (2, 3) — shape (2, 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
get_config Ran
ran on a synthesized input
cvtower/seesawfacenet_pytorch/src/config.py
code served (permissive licence) · get_code("7068d53e5a1d27e7")
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 EasyDict. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn import CrossEntropyLoss
from torchvision import transforms as trans
from pathlib import Path
from easydict import EasyDict as edict

torch.manual_seed(0)

ARGS = {
    'training': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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_reference_facial_points Ran
ran on a synthesized input
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/align_trans.py
code served (permissive licence) · get_code("a88ec2b4b2ac122c")
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 (5, 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

ARGS = {
    'output_size': (96, 112),
    'inner_padding_factor': 0.0,
    'outer_padding': (0, 0),
    'default_square': False
}
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 (5, 2) — shape (5, 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
hard_sigmoid Ran
ran, honoured the contract we drafted
pshashk/seesaw-facenet/model.py
pointer only (licence: NONE) · get_code("8b5594729a056dad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pshashk/seesaw-facenet 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.

nms Ran
ran on a synthesized input
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/box_utils.py
code served (permissive licence) · get_code("522ee6c31c17d845")
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 list, ndim 1, dtype family int; 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

# Create sample bounding boxes with scores
# Format: [xmin, ymin, xmax, ymax, score]
boxes = np.array([
    [10.0, 20.0, 50.0, 60.0, 0.9],
    [15.0, 25.0, 55.0, 65.0, 0.8],
    [100.0, 100.0, 150.0, 150.0, 0.85],
    [200.0, 200.0, 250.0, 250.0, 0.7],
], dtype=np.float32)

ARGS = {
    'boxes': boxes,
    'overlap_threshold': 0.5,
    'mode': 'union'
}
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 list, ndim 1, dtype family int — a list 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
show_bboxes Ran
ran on a synthesized input
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/visualization_utils.py
code served (permissive licence) · get_code("1a075d92bb280328")
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 Image. 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
from PIL import Image

# Create a simple PIL Image (small 100x100 RGB image)
img = Image.new('RGB', (100, 100), color='black')

# Create bounding boxes: shape [n, 5] where n=2
# Each box has [x1, y1, x2, y2, confidence]
bounding_boxes = np.array([
    [10.0, 10.0, 30.0, 30.0, 0.95],
    [40.0, 40.0, 70.0, 70.0, 0.87]
], dtype=np.float32)

# Create facial landmarks: shape [n, 10]
# Each landmark has 5 points with (x, y) coordinates
facial_landmarks = np.array([
    [15.0, 20.0, 25.0, 18.0, 22.0, 15.0, 20.0, 25.0, 18.0, 22.0],
    [45.0, 50.0, 55.0, 48.0, 52.0, 45.0, 50.0, 55.0, 48.0, 52.0]
], dtype=np.float32)

ARGS = {
    'img': img,
    'bounding_boxes': bounding_boxes,
    'facial_landmarks': facial_landmarks
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
tformfwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/matlab_cp2tform.py
code served (permissive licence) · get_code("b4e2f92e3ce5abc6")
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 (4, 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 3x3 affine transformation matrix
trans = np.array([
    [1.0, 0.0, 2.0],
    [0.0, 1.0, 3.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Create a Kx2 array of coordinates (K=4 points)
uv = np.array([
    [0.0, 0.0],
    [1.0, 1.0],
    [2.0, 3.0],
    [4.0, 5.0]
], dtype=np.float32)

ARGS = {
    "trans": trans,
    "uv": uv
}
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 (4, 2) — shape (4, 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
tforminv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/matlab_cp2tform.py
code served (permissive licence) · get_code("6661cdf22fccc11e")
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 (5, 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 simple 3x3 affine transformation matrix
# This is a valid transformation matrix for 2D homogeneous coordinates
trans = np.array([
    [1.5, 0.2, 10.0],
    [0.1, 1.3, 5.0],
    [0.0, 0.0, 1.0]
], dtype=np.float64)

# Create sample UV coordinates (Kx2 array)
# K=5 points with (x, y) coordinates
uv = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [0.0, 1.0],
    [1.0, 1.0],
    [2.5, 3.7]
], dtype=np.float64)

ARGS = {
    'trans': trans,
    'uv': uv
}
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 (5, 2) — shape (5, 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
detect_faces Not yet run
unverified (harvested, no recorded run)
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/detector.py
code served (permissive licence) · get_code("15396a0e5161d1a2")
How it ran

no invocation recorded.

run_first_stage Not yet run
unverified (harvested, no recorded run)
cvtower/seesawfacenet_pytorch/src/mtcnn_pytorch/src/first_stage.py
code served (permissive licence) · get_code("c2027475131174ef")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 0 the same month, 8 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
get_affine_transform_matrix 4 other papers
1 dated earlier, 3 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
2203.11593 (2022-03)
Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
and 1 more not named here
tformfwd 4 other papers
2 dated earlier, 2 later
1411.7923 (2014-11)
Learning Face Representation from Scratch
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
and 1 more not named here
tforminv 4 other papers
2 dated earlier, 2 later
1411.7923 (2014-11)
Learning Face Representation from Scratch
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
and 1 more not named here
calibrate_box 2 other papers
1 dated earlier, 1 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
conv_1x1_bn 2 other papers
2 dated earlier
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1806.00178 (2018-06)
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
conv_bn 2 other papers
2 dated earlier
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1806.00178 (2018-06)
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
convert_to_square 2 other papers
1 dated earlier, 1 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
findNonreflectiveSimilarity 2 other papers
2 dated earlier
1411.7923 (2014-11)
Learning Face Representation from Scratch
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
get_reference_facial_points 2 other papers
1 dated earlier, 1 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
nms 2 other papers
1 dated earlier, 1 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
show_bboxes 2 other papers
1 dated earlier, 1 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
detect_faces 1 other paper
1 dated earlier
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
run_first_stage 1 other paper
1 dated earlier
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep Convolutional Neural Network (DCNNs) come to be the most widely used solution for most computer vision related tasks, and one of the most important application scenes is face verification. Due to its high-accuracy performance, deep face verification models of which the inference stage occurs on cloud platform through internet plays the key role on most prectical scenes. However, two critical issues exist: First, individual privacy may not be well protected since they have to upload their personal photo and other private information to the online cloud backend. Secondly, either training or inference stage is time-comsuming and the latency may affect customer experience, especially when the internet link speed is not so stable or in remote areas where mobile reception is not so good, but also in cities where building and other construction may block mobile signals. Therefore, designing lightweight networks with low memory requirement and computational cost is one of the most practical solutions for face verification on mobile platform. In this paper, a novel mobile network named SeesawFaceNets, a simple but effective model, is proposed for productively deploying face recognition for mobile devices. Dense experimental results have shown that our proposed model SeesawFaceNets outperforms the baseline MobilefaceNets, with only {\bf66\%}(146M VS 221M MAdds) computational cost, smaller batch size and less training steps, and SeesawFaceNets achieve comparable performance with other SOTA model e.g. mobiface with only {\bf54.2\%}(1.3M VS 2.4M) parameters and {\bf31.6\%}(146M VS 462M MAdds) computational cost, It is also eventually competitive against large-scale deep-networks face recognition on all 5 listed public validation datasets, with {\bf6.5\%}(4.2M VS 65M) parameters and {\bf4.35\%}(526M VS 12G MAdds) computational cost.

For agents

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

get_harvested_code_for_paper("1908.09124")
get_code_for_paper("1908.09124")
have("1908.09124")

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

curl https://syntology.ai/api/ran/1908.09124.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.09124.svg)](https://syntology.ai/paper/1908.09124)

Connect an agent — have() is free.