SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.09658 · 2019

Probabilistic Face Embeddings

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure 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/1904.09658.json · badge: /api/ran/1904.09658.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
seasonSH/Probabilistic-Face-Embeddings canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
force_compare Ran
ran; our contract draft was wrong, not the code
seasonSH/Probabilistic-Face-Embeddings/evaluation/eval_ijb.py
code served (permissive licence) · get_code("0bdac68b2a0a6dcb")
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 function. 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 numpy as np

# Define a simple compare function that takes two batches and returns a score
def simple_compare_func(batch1, batch2):
    """
    A simple comparison function that takes two batches and returns a scalar score.
    batch1 and batch2 are expected to have shape (1, 4) based on the function usage.
    """
    # Convert to numpy if needed and compute a simple similarity score
    if isinstance(batch1, np.ndarray):
        b1 = batch1
    else:
        b1 = batch1.numpy() if hasattr(batch1, 'numpy') else np.array(batch1)
    
    if isinstance(batch2, np.ndarray):
        b2 = batch2
    else:
        b2 = batch2.numpy() if hasattr(batch2, 'numpy') else np.array(batch2)
    
    # Return a simple score (e.g., negative mean squared difference)
    return -np.mean((b1 - b2) ** 2)

# Create test data: two lists of items
# Each item can be a numpy array or None
t1_data = [
    np.random.randn(1, 4),
    np.random.randn(1, 4),
    None,
    np.random.randn(1, 4),
]

t2_data = [
    np.random.randn(1, 4),
    None,
    np.random.randn(1, 4),
    np.random.randn(1, 4),
]

ARGS = {
    'compare_func': simple_compare_func,
    'verbose': False,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Embedding methods have achieved success in face recognition by comparing facial features in a latent semantic space. However, in a fully unconstrained face setting, the facial features learned by the embedding model could be ambiguous or may not even be present in the input face, leading to noisy representations. We propose Probabilistic Face Embeddings (PFEs), which represent each face image as a Gaussian distribution in the latent space. The mean of the distribution estimates the most likely feature values while the variance shows the uncertainty in the feature values. Probabilistic solutions can then be naturally derived for matching and fusing PFEs using the uncertainty information. Empirical evaluation on different baseline models, training datasets and benchmarks show that the proposed method can improve the face recognition performance of deterministic embeddings by converting them into PFEs. The uncertainties estimated by PFEs also serve as good indicators of the potential matching accuracy, which are important for a risk-controlled recognition system.

For agents

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

get_harvested_code_for_paper("1904.09658")
get_code_for_paper("1904.09658")
have("1904.09658")

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

curl https://syntology.ai/api/ran/1904.09658.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.09658.svg)](https://syntology.ai/paper/1904.09658)

Connect an agent — have() is free.