SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.05235 · 2019

SoftTriple Loss: Deep Metric Learning Without Triplet Sampling

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 1 has no contract verdict; 1 failure 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/1909.05235.json · badge: /api/ran/1909.05235.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
idstcv/SoftTriple canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
QuocThangNguyen/deep-metric-learning-tsinghua-dogs reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
evaluation Ran
ran on a synthesized input
idstcv/SoftTriple/evaluation.py
code served (permissive licence) · get_code("d120bf5b3dee8b75")
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
from sklearn.cluster import KMeans
from sklearn.metrics.cluster import normalized_mutual_info_score

np.random.seed(0)

# Create small sample data
# X: feature matrix (num_samples x num_features)
# Y: class labels
num_samples = 8
num_features = 4
num_classes = 3

X = np.random.randn(num_samples, num_features).astype(np.float32)
Y = np.array([0, 0, 1, 1, 2, 2, 0, 1], dtype=np.int32)

# Kset: list of k values to evaluate recall@k
Kset = np.array([2, 4])

ARGS = {
    "X": X,
    "Y": Y,
    "Kset": Kset,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
get_embedding Ran
ran, honoured the contract we drafted
QuocThangNguyen/deep-metric-learning-tsinghua-dogs/src/infer.py
pointer only (licence: NONE) · get_code("5480fa55602d0208")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QuocThangNguyen/deep-metric-learning-tsinghua-dogs 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.

get_embeddings_from_dataloader Ran
ran; our contract draft was wrong, not the code
QuocThangNguyen/deep-metric-learning-tsinghua-dogs/src/infer.py
pointer only (licence: NONE) · get_code("613cf8184c0ccefe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QuocThangNguyen/deep-metric-learning-tsinghua-dogs 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.

bninception Not yet run
unverified (harvested, no recorded run)
idstcv/SoftTriple/net/bninception.py
code served (permissive licence) · get_code("8040266c75525c17")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of triplet constraints, a sampling strategy is essential for DML. With the tremendous success of deep learning in classifications, it has been applied for DML. When learning embeddings with deep neural networks (DNNs), only a mini-batch of data is available at each iteration. The set of triplet constraints has to be sampled within the mini-batch. Since a mini-batch cannot capture the neighbors in the original set well, it makes the learned embeddings sub-optimal. On the contrary, optimizing SoftMax loss, which is a classification loss, with DNN shows a superior performance in certain DML tasks. It inspires us to investigate the formulation of SoftMax. Our analysis shows that SoftMax loss is equivalent to a smoothed triplet loss where each class has a single center. In real-world data, one class can contain several local clusters rather than a single one, e.g., birds of different poses. Therefore, we propose the SoftTriple loss to extend the SoftMax loss with multiple centers for each class. Compared with conventional deep metric learning algorithms, optimizing SoftTriple loss can learn the embeddings without the sampling phase by mildly increasing the size of the last fully connected layer. Experiments on the benchmark fine-grained data sets demonstrate the effectiveness of the proposed loss function. Code is available at https://github.com/idstcv/SoftTriple

For agents

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

get_harvested_code_for_paper("1909.05235")
get_code_for_paper("1909.05235")
have("1909.05235")

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

curl https://syntology.ai/api/ran/1909.05235.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.05235.svg)](https://syntology.ai/paper/1909.05235)

Connect an agent — have() is free.