SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.00338 · 2018

Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 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/1809.00338.json · badge: /api/ran/1809.00338.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
ZhaoJ9014/High_Performance_Face_Recognition canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get4pts Ran
ran on a synthesized input
ZhaoJ9014/High_Performance_Face_Recognition/src/MS-C1/align.py
code served (permissive licence) · get_code("cd7d67a76db3a172")
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

def get4pts(pts):
    pts = [float(i) if float(i) > 0 else 0 for i in pts]
    a = pts[0::2]
    b = pts[1::2]
    pts = np.float32(list(zip(a, b)))
    le = (pts[1] + pts[2]) / 2
    re = (pts[3] + pts[4]) / 2
    mse = (pts[5] + pts[6]) / 2
    nse = pts[0]
    return np.float32([le, re, nse, mse])

# The function expects pts to be an iterable of numeric values
# that will be converted to floats and then reorganized
# It needs at least 14 elements (indices 0-13 are accessed: pts[0], pts[1], pts[2], pts[3], pts[4], pts[5], pts[6])
# Let's provide 14 values that will work
pts_input = [1.5, 2.0, 3.5, 4.0, 5.5, 6.0, 7.5, 8.0, 9.5, 10.0, 11.5, 12.0, 13.5, 14.0]

ARGS = {
    "pts": pts_input
}
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
get_upsampling_weight Ran
ran, honoured the contract we drafted
ZhaoJ9014/High_Performance_Face_Recognition/src/ResNet/CASIA_WEB_FACE.PyTorch/models.py
code served (permissive licence) · get_code("e475794319393649")
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 4, dtype family float, shape (3, 3, 4, 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - in_channels: used as range() and indexing into weight array - needs to be int
# - out_channels: used as range() and indexing into weight array - needs to be int
# - kernel_size: used in arithmetic and ogrid - needs to be int
# The function creates a bilinear upsampling weight tensor
# in_channels and out_channels should be equal length for the indexing to work

ARGS = {
    "in_channels": 3,
    "out_channels": 3,
    "kernel_size": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 4, dtype family float, shape (3, 3, 4, 4) — shape (3, 3, 4, 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
make_weights_for_balanced_classes Ran
ran on a synthesized input
ZhaoJ9014/High_Performance_Face_Recognition/src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py
code served (permissive licence) · get_code("c1f0ff9638b3e29f")
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 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)

# Based on the function body, `images` is a list of tuples where each tuple is (image_path, class_label)
# The function iterates over images and accesses item[1] to get the class label
# nclasses is the number of distinct classes

# Create mock images dataset in the format expected: list of (path/id, class_label) tuples
images = [
    ("img_0.jpg", 0),
    ("img_1.jpg", 0),
    ("img_2.jpg", 1),
    ("img_3.jpg", 1),
    ("img_4.jpg", 1),
    ("img_5.jpg", 2),
]

nclasses = 3

ARGS = {
    "images": images,
    "nclasses": nclasses,
}
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 list, ndim 1, dtype family float — 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
rotate Ran
ran on a synthesized input
ZhaoJ9014/High_Performance_Face_Recognition/src/MS-C1/align.py
code served (permissive licence) · get_code("997ecf00348e78b9")
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 cv2

# Create a small test image (3x4 with 3 channels)
img = np.random.randint(0, 255, (100, 120, 3), dtype=np.uint8)

# Create landmarks array with 4 points (left eye, right eye, unused, mouth/center)
# Each point is [x, y]
lmk = np.array([
    [40, 30],      # left eye center
    [80, 30],      # right eye center
    [60, 50],      # unused point
    [60, 70],      # mouth/center point
], dtype=np.float32)

ARGS = {
    "img": img,
    "lmk": lmk,
}
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 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
savgol_smooth Ran
ran on a synthesized input
ZhaoJ9014/High_Performance_Face_Recognition/src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py
code served (permissive licence) · get_code("2788c94fffe8ae7c")
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 (10,) 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
import scipy.signal

torch.manual_seed(0)

# Construct arguments for savgol_smooth function
# The function takes y (array-like data) and box_pts (window size)

# y should be a 1D array-like object that savgol_filter can process
y = np.array([1.0, 2.5, 3.1, 4.2, 5.0, 4.8, 3.9, 2.1, 1.5, 0.8])

# box_pts should be an integer representing the window size for the Savitzky-Golay filter
# It must be odd or will be incremented to odd in the function
box_pts = 5

ARGS = {
    "y": y,
    "box_pts": box_pts
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — 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 (10,) — shape (10,) 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_vgg_class_counts Not yet run
unverified (harvested, no recorded run)
ZhaoJ9014/High_Performance_Face_Recognition/src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py
code served (permissive licence) · get_code("6fd1465a309afa5f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 5 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_upsampling_weight 9 other papers
1 dated earlier, 8 later
1807.09856 (2018-07)
Where are the Blobs: Counting by Localization with Point Supervision
2006.00176 (2020-06)
When2com: Multi-Agent Perception via Communication Graph Grouping
2007.11782 (2020-07)
Accurate RGB-D Salient Object Detection via Collaborative Learning
and 6 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

Despite the remarkable progress in face recognition related technologies, reliably recognizing faces across ages still remains a big challenge. The appearance of a human face changes substantially over time, resulting in significant intra-class variations. As opposed to current techniques for age-invariant face recognition, which either directly extract age-invariant features for recognition, or first synthesize a face that matches target age before feature extraction, we argue that it is more desirable to perform both tasks jointly so that they can leverage each other. To this end, we propose a deep Age-Invariant Model (AIM) for face recognition in the wild with three distinct novelties. First, AIM presents a novel unified deep architecture jointly performing cross-age face synthesis and recognition in a mutual boosting way. Second, AIM achieves continuous face rejuvenation/aging with remarkable photorealistic and identity-preserving properties, avoiding the requirement of paired data and the true age of testing samples. Third, we develop effective and novel training strategies for end-to-end learning the whole deep architecture, which generates powerful age-invariant face representations explicitly disentangled from the age variation. Moreover, we propose a new large-scale Cross-Age Face Recognition (CAFR) benchmark dataset to facilitate existing efforts and push the frontiers of age-invariant face recognition research. Extensive experiments on both our CAFR and several other cross-age datasets (MORPH, CACD and FG-NET) demonstrate the superiority of the proposed AIM model over the state-of-the-arts. Benchmarking our model on one of the most popular unconstrained face recognition datasets IJB-C additionally verifies the promising generalizability of AIM in recognizing faces in the wild.

For agents

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

get_harvested_code_for_paper("1809.00338")
get_code_for_paper("1809.00338")
have("1809.00338")

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

curl https://syntology.ai/api/ran/1809.00338.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.00338.svg)](https://syntology.ai/paper/1809.00338)

Connect an agent — have() is free.