SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.19293 · 2024

VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 0 have no contract verdict; 7 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/2409.19293.json · badge: /api/ran/2409.19293.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
ahmedest61/vlad-buff canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_triplet_margin Ran
ran, honoured the contract we drafted
ahmedest61/vlad-buff/cluster_analysis.py
pointer only (licence: GPL-3.0) · get_code("df9181a5834a1c01")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

extract_method_name Ran
ran; our contract draft was wrong, not the code
ahmedest61/vlad-buff/predictions.py
pointer only (licence: GPL-3.0) · get_code("ae3f9d105c3931b8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

getWeights Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ahmedest61/vlad-buff/models/aggregators/aggregation.py
pointer only (licence: GPL-3.0) · get_code("4a6f2e73c5fe4b76")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

input_transform Ran
ran; our contract draft was wrong, not the code
ahmedest61/vlad-buff/dataloaders/PittsburgDataset.py
pointer only (licence: GPL-3.0) · get_code("0bfa87e7ee328290")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

parse_args Ran
ran; our contract draft was wrong, not the code
ahmedest61/vlad-buff/hubconf.py
pointer only (licence: GPL-3.0) · get_code("890961077e804998")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

pca Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ahmedest61/vlad-buff/add_pca.py
pointer only (licence: GPL-3.0) · get_code("91cb29e9b0c3ad52")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

replace_key Ran
ran; our contract draft was wrong, not the code
ahmedest61/vlad-buff/hubconf.py
pointer only (licence: GPL-3.0) · get_code("6d2b2fe7541bd5a4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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.

visualize_pixel_intensities Ran
ran; our contract draft was wrong, not the code
ahmedest61/vlad-buff/cluster_analysis.py
pointer only (licence: GPL-3.0) · get_code("7ce2bd7ce8164f05")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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_250k_val_set Not yet run
unverified (harvested, no recorded run)
ahmedest61/vlad-buff/dataloaders/PittsburgDataset.py
pointer only (licence: GPL-3.0) · get_code("5228e90ed5d72209")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

get_recalls Not yet run
unverified (harvested, no recorded run)
ahmedest61/vlad-buff/predictions.py
pointer only (licence: GPL-3.0) · get_code("ef39dfe25962e8cd")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

get_whole_val_set Not yet run
unverified (harvested, no recorded run)
ahmedest61/vlad-buff/dataloaders/PittsburgDataset.py
pointer only (licence: GPL-3.0) · get_code("4aad74292f273387")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ahmedest61/vlad-buff, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
get_250k_val_set 2 other papers
2 dated earlier
2311.15937 (2023-11)
Optimal Transport Aggregation for Visual Place Recognition
2407.02422 (2024-07)
Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition
get_whole_val_set 2 other papers
2 dated earlier
2311.15937 (2023-11)
Optimal Transport Aggregation for Visual Place Recognition
2407.02422 (2024-07)
Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition
input_transform 2 other papers
2 dated earlier
2311.15937 (2023-11)
Optimal Transport Aggregation for Visual Place Recognition
2407.02422 (2024-07)
Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition

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

Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The current state-of-the-art VPR methods rely on VLAD aggregation, which can be trained to learn a weighted contribution of features through their soft assignment to cluster centers. However, this process has two key limitations. Firstly, the feature-to-cluster weighting does not account for over-represented repetitive structures within a cluster, e.g., shadows or window panes; this phenomenon is also referred to as the `burstiness' problem, classically solved by discounting repetitive features before aggregation. Secondly, feature to cluster comparisons are compute-intensive for state-of-the-art image encoders with high-dimensional local features. This paper addresses these limitations by introducing VLAD-BuFF with two novel contributions: i) a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training, and ii) Fast Feature aggregation by reducing local feature dimensions specifically through PCA-initialized learnable pre-projection. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall. Through additional qualitative studies, we show how our proposed weighting method effectively downweights the non-distinctive features. Source code: https://github.com/Ahmedest61/VLAD-BuFF/.

For agents

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

get_harvested_code_for_paper("2409.19293")
get_code_for_paper("2409.19293")
have("2409.19293")

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

curl https://syntology.ai/api/ran/2409.19293.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.19293.svg)](https://syntology.ai/paper/2409.19293)

Connect an agent — have() is free.