Papers › Robust and Decomposable Average Precision for Image Retrieval

Robust and Decomposable Average Precision for Image Retrieval

1 Oct 2021NeurIPS 2021 12arXiv:2110.01445archive 2025-07-28

Elias Ramzi, Nicolas Thome, Clément Rambour, Nicolas Audebert, Xavier Bitot

In image retrieval, standard evaluation metrics rely on score ranking, e.g. average precision (AP). In this paper, we introduce a method for robust and decomposable average precision (ROADMAP) addressing two major challenges for end-to-end training of deep neural networks with AP: non-differentiability and non-decomposability. Firstly, we propose a new differentiable approximation of the rank function, which provides an upper bound of the AP loss and ensures robust training. Secondly, we design a simple yet effective loss function to reduce the decomposability gap between the AP in the whole training set and its averaged batch approximation, for which we provide theoretical guarantees. Extensive experiments conducted on three image retrieval datasets show that ROADMAP outperforms several recent AP approximation methods and highlight the importance of our two contributions. Finally, using ROADMAP for training deep models yields very good performances, outperforming state-of-the-art results on the three datasets.

PaperPDFConference PDFCodeCode 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="2110.01445")

Code

Syntology Ran 4 of 5 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong.

By repository: official repository: 5 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

elias-ramzi/roadmap officialmentioned in papermentioned on GitHubpytorchMIT 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

5 samples harvested; 4 ran; 1 honoured the contract we drafted; 1 has 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 · honoured contract
3ran · our draft was wrong
1unverified

Licence: 0 of the 5 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 elias-ramzi/roadmap. “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.

get_color_distortion elias-ramzi/roadmap/roadmap/datasets/base_dataset.py official repository ran · our draft was wrong MIT (permissive) · b8ef2b49a369cb69 · report
heaviside elias-ramzi/roadmap/roadmap/losses/smooth_rank_ap.py official repository ran · honoured contract fingerprinted MIT (permissive) · a2a835592cd98f2b · report
rank elias-ramzi/roadmap/roadmap/losses/blackbox_ap.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 2e1e2e8c543195f7 · report
rank_normalised elias-ramzi/roadmap/roadmap/losses/blackbox_ap.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · ed49cae4f66fd45c · report
tau_sigmoid elias-ramzi/roadmap/roadmap/losses/smooth_rank_ap.py official repository unverified MIT (permissive) · 74f2a948e1eb6041 · report

Tasks

Image RetrievalMetric LearningRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval CUB-200-2011 ROADMAP (Deit-B) R@1 77.4 #2 of 8 Archive leaderboard report
Image Retrieval CUB-200-2011 ROADMAP (ResNet-50) R@1 68.5 #4 of 8 Archive leaderboard report
Image Retrieval SOP ROADMAP (DeiT-B) R@1 86.0 #2 of 14 Archive leaderboard report
Image Retrieval SOP ROADMAP (ResNet-50) R@1 83.1 #4 of 14 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (DeiT-S) R@1 73.6 #4 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (DeiT-S) R@16 93.1 #4 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (DeiT-S) R@32 95.2 #4 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (DeiT-S) R@5 86.2 #4 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (ResNet-50) R@1 69.1 #8 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (ResNet-50) R@16 91.3 #8 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (ResNet-50) R@32 93.9 #8 of 10 Archive leaderboard report
Image Retrieval iNaturalist ROADMAP (ResNet-50) R@5 83.1 #8 of 10 Archive leaderboard report
Metric Learning Stanford Online Products ROADMAP (DeiT-S) R@1 86.0 #5 of 33 Archive leaderboard report
Metric Learning Stanford Online Products ROADMAP (ResNet-50) R@1 83.1 #9 of 33 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.

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