SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.02244 · ICCV · 2021

Self-supervised Product Quantization for Deep Unsupervised Image Retrieval

Nam Cho, Young Jang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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 2 have no contract verdict; 0 failures of our instrument; 3 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/2109.02244.json · badge: /api/ran/2109.02244.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
youngkyunJang/SPQ canonical (classifier label)
classifier basis: census
2 ran · 3 no recorded run
FunctionStatusWhere it lives
Soft_Quantization Ran
ran on a synthesized input
youngkyunJang/SPQ/utils.py
code served (permissive licence) · get_code("9e97433ebda9365c")
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 2, dtype family float, shape (2, 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 torch.nn.functional as F

torch.manual_seed(0)

# Construct valid arguments for Soft_Quantization(X, C, N_books, tau_q)

# Parameters:
# X: Nxd matrix (batch of data points)
# C: codebook matrix, shape should be compatible with N_books splits
# N_books: number of codebooks
# tau_q: temperature parameter for softmax

N_books = 2
L_word = 2  # dimension per codebook
d = N_books * L_word  # total dimension = 4

# X: batch size 2, dimension 4
X = torch.randn(2, d)

# C: codebook with N_books codebooks, each with L_word dimensions
# Let's create a codebook with 3 codewords per book
C = torch.randn(3, d)

# Temperature parameter
tau_q = 1.0

ARGS = {
    "X": X,
    "C": C,
    "N_books": N_books,
    "tau_q": tau_q
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
squared_distances Ran
ran on a synthesized input
youngkyunJang/SPQ/utils.py
code served (permissive licence) · get_code("e72045686bd0fbe2")
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 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 torch as T

T.manual_seed(0)

# x is an Nxd matrix
x = T.randn(2, 4)

# y is an Mxd matrix
y = T.randn(3, 4)

ARGS = {
    "x": x,
    "y": y,
}
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 Tensor, 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
Evaluate_mAP Not yet run
unverified (harvested, no recorded run)
youngkyunJang/SPQ/Retrieval.py
code served (permissive licence) · get_code("8965599eae16ff64")
How it ran

no invocation recorded.

Indexing Not yet run
unverified (harvested, no recorded run)
youngkyunJang/SPQ/Retrieval.py
code served (permissive licence) · get_code("0d4aab6cb8ae5bd1")
How it ran

no invocation recorded.

pqDist_one Not yet run
unverified (harvested, no recorded run)
youngkyunJang/SPQ/Retrieval.py
code served (permissive licence) · get_code("7c26ee9dd52155b6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 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.

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

Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared to the conventional methods. However, it is painstaking to assign labels precisely for a vast amount of training data, and also, the annotation process is error-prone. To tackle these issues, we propose the first deep unsupervised image retrieval method dubbed Self-supervised Product Quantization (SPQ) network, which is label-free and trained in a self-supervised manner. We design a Cross Quantized Contrastive learning strategy that jointly learns codewords and deep visual descriptors by comparing individually transformed images (views). Our method analyzes the image contents to extract descriptive features, allowing us to understand image representations for accurate retrieval. By conducting extensive experiments on benchmarks, we demonstrate that the proposed method yields state-of-the-art results even without supervised pretraining.

For agents

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

get_harvested_code_for_paper("2109.02244")
get_code_for_paper("2109.02244")
have("2109.02244")

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

curl https://syntology.ai/api/ran/2109.02244.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.02244.svg)](https://syntology.ai/paper/2109.02244)

Connect an agent — have() is free.