SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13172 · 2020

Learning and aggregating deep local descriptors for instance-level recognition

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 2 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/2007.13172.json · badge: /api/ran/2007.13172.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
gtolias/how canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
jenicek/asmk reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
build_ivf Ran
ran; our contract draft was wrong, not the code
jenicek/asmk/examples/demo_how.py
code served (permissive licence) · get_code("e5f0920c6b5c8cdb")
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 MockASMK. 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
from unittest.mock import MagicMock
import logging

torch.manual_seed(0)

# Create a mock ASMK object with build_ivf method
class MockASMK:
    def __init__(self):
        self.metadata = {}
    
    def build_ivf(self, vecs, imids, cache_path=None):
        # Simulate the build_ivf operation
        self.metadata['build_ivf'] = {
            'index_time': 1.23,
            'ivf_stats': {'nlist': 256, 'indexed_vectors': len(vecs)}
        }
        return self

# Create mock descriptor dict
desc = {
    'vecs': torch.randn(8, 4),  # 8 descriptors, 4 dims
    'imids': np.array([0, 1, 2, 3, 4, 5, 6, 7])  # image ids
}

# Create mock globals dict
globals_dict = {
    'exp_path': '/tmp/exp'
}

# Create mock logger
logger = logging.getLogger('test')
logger.setLevel(logging.DEBUG)
handler = logging.StreamHandler()
logger.addHandler(handler)

# Create mock asmk object
asmk = MockASMK()

# Create dataset string
dataset = 'test_dataset'

# Build ARGS dictionary with all parameters
ARGS = {
    'asmk': asmk,
    'dataset': dataset,
    'desc': desc,
    'globals': globals_dict,
    'logger': logger
}
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 MockASMK — a MockASMK output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockASMK 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
extract_vectors Not yet run
unverified (harvested, no recorded run)
gtolias/how/how/networks/how_net.py
code served (permissive licence) · get_code("32d92b9a890f1f6f")
How it ran

no invocation recorded.

extract_vectors_local Not yet run
unverified (harvested, no recorded run)
gtolias/how/how/networks/how_net.py
code served (permissive licence) · get_code("02febcafd9b9ea5f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled global image descriptors. At inference, the local descriptors are provided by the activations of internal components of the network. We demonstrate why such an approach learns local descriptors that work well for image similarity estimation with classical efficient match kernel methods. The experimental validation studies the trade-off between performance and memory requirements of the state-of-the-art image search approach based on match kernels. Compared to existing local descriptors, the proposed ones perform better in two instance-level recognition tasks and keep memory requirements lower. We experimentally show that global descriptors are not effective enough at large scale and that local descriptors are essential. We achieve state-of-the-art performance, in some cases even with a backbone network as small as ResNet18.

For agents

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

get_harvested_code_for_paper("2007.13172")
get_code_for_paper("2007.13172")
have("2007.13172")

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

curl https://syntology.ai/api/ran/2007.13172.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13172.svg)](https://syntology.ai/paper/2007.13172)

Connect an agent — have() is free.