SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.06897 · 2020

Adaptive-Attentive Geolocalization from few queries: a hybrid approach

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 4 have no contract verdict; 1 failure 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/2010.06897.json · badge: /api/ran/2010.06897.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
valeriopaolicelli/AdAGeo canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran on a synthesized input
valeriopaolicelli/AdAGeo/src/datasets.py
code served (permissive licence) · get_code("e65e7c12dc276527")
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 torch
import torch.utils.data as data
import itertools

torch.manual_seed(0)

# Create sample batch data
# Each item is a tuple of (query, positive, negatives, indices)
# query: (3, 4, 5) - 3 channels, 4x5 spatial
# positive: (3, 4, 5)
# negatives: (n, 3, 4, 5) - n negative samples
# indices: list of indices

batch_item_1 = (
    torch.randn(3, 4, 5),  # query
    torch.randn(3, 4, 5),  # positive
    torch.randn(2, 3, 4, 5),  # negatives (2 negative samples)
    [0, 1]  # indices
)

batch_item_2 = (
    torch.randn(3, 4, 5),  # query
    torch.randn(3, 4, 5),  # positive
    torch.randn(3, 3, 4, 5),  # negatives (3 negative samples)
    [2, 3, 4]  # indices
)

# Create the batch as a list of tuples
batch = [batch_item_1, batch_item_2]

ARGS = {
    "batch": batch
}
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 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
valeriopaolicelli/AdAGeo/src/resnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository 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_clusters Ran
ran on a synthesized input
valeriopaolicelli/AdAGeo/src/util.py
code served (permissive licence) · get_code("67f34e56113899a8")
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 torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from torch.utils.data import Dataset
from math import ceil

torch.manual_seed(0)

# Build a minimal model that supports the required interface
class MinimalModel(nn.Module):
    def __init__(self, encoder_dim):
        super().__init__()
        self.encoder_dim = encoder_dim
        self.conv = nn.Conv2d(3, encoder_dim, kernel_size=1)
    
    def forward(self, x, mode='feat'):
        # x shape: (batch_size, 3, H, W)
        # Output shape: (batch_size, encoder_dim, H', W')
        return self.conv(x)
    
    def eval(self):
        return super().eval()
    
    def to(self, device):
        return super().to(device)

# Build a minimal cluster dataset
class MinimalClusterDataset(Dataset):
    def __init__(self, num_samples=100):
        self.num_samples = num_samples
        self.db_struct = type('obj', (object,), {'num_gallery': num_samples})()
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        # Return (input tensor, index)
        input_tensor = torch.randn(3, 8, 8)  # 3 channels, 8x8 spatial
        return input_tensor, idx

# Build args object
class ArgsConfig:
    def __init__(self):
        self.train_q = 'regular'  # not 'biost'
        self.num_workers = 0
        self.cache_batch_size = 2
        self.device = 'cpu'
        self.attention = False
        self.encoder_dim = 4
        self.num_clusters = 8

# Construct the arguments
encoder_dim = 4
model = MinimalModel(encoder_dim=encoder_dim)
cluster_set = MinimalClusterDataset(num_samples=100)
args = ArgsConfig()

ARGS = {
    'args': args,
    'cluster_set': cluster_set,
    'model': model,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
faiss, numpy, torch, tqdm — 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_discriminator Ran
ran on a synthesized input
valeriopaolicelli/AdAGeo/src/grl_util.py
code served (permissive licence) · get_code("8863d45315243613")
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 Sequential. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "input_dim": 256,
    "num_classes": 2
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
resume_train Ran
ran on a synthesized input
valeriopaolicelli/AdAGeo/src/util.py
code served (permissive licence) · get_code("9b3b4018695fb2f7")
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, 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
import torch.nn as nn
import tempfile
import os

torch.manual_seed(0)

# Create a minimal model
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal optimizer
model = MinimalModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a checkpoint file
checkpoint = {
    'epoch': 5,
    'state_dict': model.state_dict(),
    'best_score': 85.5,
    'optimizer': optimizer.state_dict()
}

# Save checkpoint to a temporary file
temp_dir = tempfile.gettempdir()
checkpoint_path = os.path.join(temp_dir, 'test_checkpoint.pt')
torch.save(checkpoint, checkpoint_path)

# Create args object with resume attribute
class Args:
    def __init__(self, resume_path):
        self.resume = resume_path

args = Args(checkpoint_path)

ARGS = {
    'args': args,
    'model': model,
    'optimizer': optimizer
}
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 tuple, ndim 1, dtype family float — a tuple 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
download_file_from_google_drive Not yet run
unverified (harvested, no recorded run)
valeriopaolicelli/AdAGeo/src/download_and_unzip_svox.py
code served (permissive licence) · get_code("ca4b3589df891c00")
How it ran

no invocation recorded.

parse_db_struct Not yet run
unverified (harvested, no recorded run)
valeriopaolicelli/AdAGeo/src/datasets.py
code served (permissive licence) · get_code("71cf99eb3953374b")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
valeriopaolicelli/AdAGeo/src/resnet.py
code served (permissive licence) · get_code("95408b7468eba855")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 7 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
conv3x3 686 other papers
261 dated earlier, 7 the same month, 417 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 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

We address the task of cross-domain visual place recognition, where the goal is to geolocalize a given query image against a labeled gallery, in the case where the query and the gallery belong to different visual domains. To achieve this, we focus on building a domain robust deep network by leveraging over an attention mechanism combined with few-shot unsupervised domain adaptation techniques, where we use a small number of unlabeled target domain images to learn about the target distribution. With our method, we are able to outperform the current state of the art while using two orders of magnitude less target domain images. Finally we propose a new large-scale dataset for cross-domain visual place recognition, called SVOX. The pytorch code is available at https://github.com/valeriopaolicelli/AdAGeo .

For agents

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

get_harvested_code_for_paper("2010.06897")
get_code_for_paper("2010.06897")
have("2010.06897")

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

curl https://syntology.ai/api/ran/2010.06897.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.06897.svg)](https://syntology.ai/paper/2010.06897)

Connect an agent — have() is free.