Papers › ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

2 Apr 2020ECCV 2020 8arXiv:2004.01113archive 2025-07-28

Eu Wern Teh, Terrance DeVries, Graham W. Taylor

We consider the problem of distance metric learning (DML), where the task is to learn an effective similarity measure between images. We revisit ProxyNCA and incorporate several enhancements. We find that low temperature scaling is a performance-critical component and explain why it works. Besides, we also discover that Global Max Pooling works better in general when compared to Global Average Pooling. Additionally, our proposed fast moving proxies also addresses small gradient issue of proxies, and this component synergizes well with low temperature scaling and Global Max Pooling. Our enhanced model, called ProxyNCA++, achieves a 22.9 percentage point average improvement of Recall@1 across four different zero-shot retrieval datasets compared to the original ProxyNCA algorithm. Furthermore, we achieve state-of-the-art results on the CUB200, Cars196, Sop, and InShop datasets, achieving Recall@1 scores of 72.2, 90.1, 81.4, and 90.9, respectively.

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="2004.01113")

Code

Syntology Ran 0 of 5 code samples harvested from 1 repository linked to this paper; 5 have no recorded run.

By repository: community (archive-listed): 5 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

euwern/proxynca_pp mentioned 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; 0 ran; 0 honoured the contract we drafted; 5 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.

5unverified

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 euwern/proxynca_pp. “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.

binarize_and_smooth_labels euwern/proxynca_pp/loss.py community (archive-listed) unverified MIT (permissive) · cff1ce4645740206 · report
load_config euwern/proxynca_pp/utils.py community (archive-listed) unverified MIT (permissive) · 0d1bc17f353a5a5e · report
pairwise_distance euwern/proxynca_pp/similarity.py community (archive-listed) unverified MIT (permissive) · ecd1d401911526d0 · report
predict_batchwise euwern/proxynca_pp/utils.py community (archive-listed) unverified MIT (permissive) · c89e3e64eac56c8b · report
predict_batchwise_inshop euwern/proxynca_pp/utils.py community (archive-listed) unverified MIT (permissive) · 6d8f0f85042ae81c · report

Tasks

Image RetrievalMetric LearningRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval CARS196 ProxyNCA++ R@1 90.1 #2 of 8 Archive leaderboard report
Image Retrieval CUB-200-2011 ProxyNCA++ R@1 72.2 #3 of 8 Archive leaderboard report
Image Retrieval In-Shop ProxyNCA++ R@1 90.9 #3 of 7 Archive leaderboard report
Image Retrieval SOP ProxyNCA++ R@1 81.4 #5 of 14 Archive leaderboard report
Metric Learning CARS196 ResNet-50 + ProxyNCA++ R@1 86.5 #23 of 36 Archive leaderboard report
Metric Learning CUB-200-2011 ResNet-50 + ProxyNCA++ R@1 69.0 #15 of 30 Archive leaderboard report
Metric Learning In-Shop ResNet-50 + ProxyNCA++ R@1 90.9 #12 of 15 Archive leaderboard report
Metric Learning Stanford Online Products ResNet-50 + ProxyNCA++ R@1 80.7 #21 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.

Methods

Average PoolingGlobal Average PoolingMax Pooling

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