Papers › Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

21 Mar 2022CVPR 2022 1arXiv:2203.10833archive 2025-07-28

Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov, Nicu Sebe, Ivan Oseledets

Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The common recipe is to use an encoder to extract embeddings and a distance-based loss function to match the representations -- usually, the Euclidean distance is utilized. An emerging interest in learning hyperbolic data embeddings suggests that hyperbolic geometry can be beneficial for natural data. Following this line of work, we propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. These embeddings are directly optimized using modified pairwise cross-entropy loss. We evaluate the proposed model with six different formulations on four datasets achieving the new state-of-the-art performance. The source code is available at https://github.com/htdt/hyp_metric.

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="2203.10833")

Code

Syntology Ran 4 of 6 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 6 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.

htdt/hyp_metric officialmentioned in papermentioned on GitHubpytorch report
OML-Team/open-metric-learning 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

6 samples harvested; 4 ran; 0 honoured the contract we drafted; 2 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 · our draft was wrong
2ran
2unverified

Licence: 0 of the 6 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 htdt/hyp_metric. “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.

HypLinear htdt/hyp_metric/hyptorch/nn.py official repository ran MIT (permissive) · ef850ea4ebf99283 · report
artanh htdt/hyp_metric/hyptorch/nn.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · daf212010121f13d · report
mobius_add htdt/hyp_metric/hyptorch/nn.py official repository ran · our draft was wrong MIT (permissive) · d0bcd7cd164a4987 · report
mobius_matvec htdt/hyp_metric/hyptorch/nn.py official repository ran MIT (permissive) · ea6109a03ce10561 · report
Artanh htdt/hyp_metric/hyptorch/nn.py official repository unverified MIT (permissive) · 7b7b467a36348c8b · report
_mobius_matvec htdt/hyp_metric/hyptorch/nn.py official repository unverified MIT (permissive) · 93968601ef4b16be · report

Tasks

Metric Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Metric Learning CARS196 Hyp-DINO 8x8 R@1 92.8 #2 of 36 Archive leaderboard report
Metric Learning CARS196 Hyp-DINO R@1 89.2 #13 of 36 Archive leaderboard report
Metric Learning CARS196 Hyp-ViT R@1 86.5 #25 of 36 Archive leaderboard report
Metric Learning CUB-200-2011 Hyp-DINO R@1 80.9 #1 of 2 Archive leaderboard report
Metric Learning CUB-200-2011 Hyp-ViT R@1 85.6 #3 of 30 Archive leaderboard report
Metric Learning In-Shop Hyp-ViT R@1 92.5 #4 of 15 Archive leaderboard report
Metric Learning In-Shop Hyp-DINO R@1 92.4 #5 of 15 Archive leaderboard report
Metric Learning Stanford Online Products Hyp-ViT R@1 85.9 #6 of 33 Archive leaderboard report
Metric Learning Stanford Online Products Hyp-DINO R@1 85.1 #7 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

DINOInfoNCEVision Transformer

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