Papers › Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval

Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval

23 Jul 2020ECCV 2020 8arXiv:2007.12163archive 2025-07-28

Andrew Brown, Weidi Xie, Vicky Kalogeiton, Andrew Zisserman

Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods. To this end, we introduce an objective that optimises instead a smoothed approximation of AP, coined Smooth-AP. Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation. We also present an analysis for why directly optimising the ranking based metric of AP offers benefits over other deep metric learning losses. We apply Smooth-AP to standard retrieval benchmarks: Stanford Online products and VehicleID, and also evaluate on larger-scale datasets: INaturalist for fine-grained category retrieval, and VGGFace2 and IJB-C for face retrieval. In all cases, we improve the performance over the state-of-the-art, especially for larger-scale datasets, thus demonstrating the effectiveness and scalability of Smooth-AP to real-world scenarios.

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="2007.12163")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: community (archive-listed): 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

interestingzhuo/foodretreival mentioned on GitHubpytorch 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

2 samples harvested; 2 ran; 2 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.

2ran · honoured contract

Licence: 0 of the 2 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 Andrew-Brown1/Smooth_AP. “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.

compute_aff Andrew-Brown1/Smooth_AP/src/Smooth_AP_loss.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · b7c1e0e2088a865e · report
sigmoid Andrew-Brown1/Smooth_AP/src/Smooth_AP_loss.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 4b3a13b8aba7b6dc · report

Tasks

Image Instance RetrievalImage RetrievalMetric LearningRetrievalVehicle Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval SOP Smooth-AP R@1 80.1 #8 of 14 Archive leaderboard report
Image Retrieval iNaturalist Smooth-AP R@1 67.2 #9 of 10 Archive leaderboard report
Image Retrieval iNaturalist Smooth-AP R@16 90.3 #9 of 10 Archive leaderboard report
Image Retrieval iNaturalist Smooth-AP R@32 93.1 #9 of 10 Archive leaderboard report
Image Retrieval iNaturalist Smooth-AP R@5 81.8 #9 of 10 Archive leaderboard report
Vehicle Re-Identification VehicleID Large Smooth-AP Rank-1 91.9 #5 of 10 Archive leaderboard report
Vehicle Re-Identification VehicleID Large Smooth-AP Rank-5 96.2 #5 of 10 Archive leaderboard report
Vehicle Re-Identification VehicleID Medium Smooth-AP Rank-1 93.3 #5 of 9 Archive leaderboard report
Vehicle Re-Identification VehicleID Medium Smooth-AP Rank-5 96.4 #5 of 9 Archive leaderboard report
Vehicle Re-Identification VehicleID Small Smooth-AP Rank-1 94.9 #5 of 13 Archive leaderboard report
Vehicle Re-Identification VehicleID Small Smooth-AP Rank-5 97.6 #5 of 13 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