Papers › AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval

6 Aug 2024arXiv:2408.03282archive 2025-07-28

Pavel Suma, Giorgos Kordopatis-Zilos, Ahmet Iscen, Giorgos Tolias

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance enhancements, this work prioritizes the crucial trade-off between performance and memory requirements. The proposed model uses a transformer-based architecture designed to estimate image-to-image similarity by capturing interactions within and across images based on their local descriptors. A distinctive property of the model is the capability for asymmetric similarity estimation. Database images are represented with a smaller number of descriptors compared to query images, enabling performance improvements without increasing memory consumption. To ensure adaptability across different applications, a universal model is introduced that adjusts to a varying number of local descriptors during the testing phase. Results on standard benchmarks demonstrate the superiority of our approach over both hand-crafted and learned models. In particular, compared with current state-of-the-art methods that overlook their memory footprint, our approach not only attains superior performance but does so with a significantly reduced memory footprint. The code and pretrained models are publicly available at: https://github.com/pavelsuma/ames

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2408.03282")

Code

Syntology Ran 13 of 13 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 12 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pavelsuma/ames officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 13 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
12ran

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from pavelsuma/ames. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_receptive_boxes pavelsuma/ames/extract/extract_cvnet.py official repository ran Apache-2.0 (permissive) · aee9e3a7b1b42f70 · report
calculate_receptive_boxes pavelsuma/ames/extract/extract_dino.py official repository ran Apache-2.0 (permissive) · e0ea19cb7ca9d5a7 · report
color_norm pavelsuma/ames/extract/transforms.py official repository ran Apache-2.0 (permissive) · d160a205c24a70f9 · report
combine pavelsuma/ames/extract/merge_hdf5.py official repository ran Apache-2.0 (permissive) · 50ad0cb6c181e867 · report
find_divisors pavelsuma/ames/extract/extract_dino.py official repository ran fingerprinted Apache-2.0 (permissive) · 04a2af9d93b09d8c · report
generate_coordinates pavelsuma/ames/extract/extract_cvnet.py official repository ran fingerprinted Apache-2.0 (permissive) · f75959fc6c795680 · report
horizontal_flip pavelsuma/ames/extract/transforms.py official repository ran Apache-2.0 (permissive) · 6f9305ce535ed9d3 · report
load_or_combine pavelsuma/ames/extract/prepare_topk_global.py official repository ran Apache-2.0 (permissive) · 0412a457791220ef · report
load_paths pavelsuma/ames/extract/prepare_topk_global.py official repository ran Apache-2.0 (permissive) · 1f32bbb8f8d33681 · report
non_maxima_suppression_2d pavelsuma/ames/extract/extract_cvnet.py official repository ran Apache-2.0 (permissive) · 79817d036d710336 · report
non_maxima_suppression_2d pavelsuma/ames/extract/extract_dino.py official repository ran Apache-2.0 (permissive) · bf31e950a3af0841 · report
read_imlist pavelsuma/ames/extract/image_dataset.py official repository ran Apache-2.0 (permissive) · a93a2142c18e2e88 · report
zero_pad pavelsuma/ames/extract/transforms.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 8e712c383c677282 · report

Tasks

Image RetrievalRe-RankingRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval Google Landmarks Dataset v2 (retrieval, testing) AMES mAP@100 37.8 #1 of 4 Archive leaderboard report
Image Retrieval ROxford (Hard) AMES mAP 80 #2 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) AMES mAP 90.7 #1 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) AMES mAP 89.7 #1 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) AMES mAP 94.9 #1 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections