Papers › Improving Deep Metric Learning by Divide and Conquer

Improving Deep Metric Learning by Divide and Conquer

9 Sep 2021arXiv:2109.04003archive 2025-07-28

Artsiom Sanakoyeu, Pingchuan Ma, Vadim Tschernezki, Björn Ommer

Deep metric learning (DML) is a cornerstone of many computer vision applications. It aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far from another. The target similarity on the training data is defined by user in form of ground-truth class labels. However, while the embedding space learns to mimic the user-provided similarity on the training data, it should also generalize to novel categories not seen during training. Besides user-provided groundtruth training labels, a lot of additional visual factors (such as viewpoint changes or shape peculiarities) exist and imply different notions of similarity between objects, affecting the generalization on the images unseen during training. However, existing approaches usually directly learn a single embedding space on all available training data, struggling to encode all different types of relationships, and do not generalize well. We propose to build a more expressive representation by jointly splitting the embedding space and the data hierarchically into smaller sub-parts. We successively focus on smaller subsets of the training data, reducing its variance and learning a different embedding subspace for each data subset. Moreover, the subspaces are learned jointly to cover not only the intricacies, but the breadth of the data as well. Only after that, we build the final embedding from the subspaces in the conquering stage. The proposed algorithm acts as a transparent wrapper that can be placed around arbitrary existing DML methods. Our approach significantly improves upon the state-of-the-art on image retrieval, clustering, and re-identification tasks evaluated using CUB200-2011, CARS196, Stanford Online Products, In-shop Clothes, and PKU VehicleID datasets.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

compvis/metric-learning-divide-and-conquer-improved officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 12 ran (2 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
10ran
4unverified

Licence: 2 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from compvis/metric-learning-divide-and-conquer-improved. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

compvis/metric-learning-divide-and-conquer-improved official repository 16 samples, 12 ran (2 instrument-failed) · 4 unverified
empty_if_default experiment/margin_loss_resnet50.py ran MIT (permissive) · f35dabf7a95feead · report fixture: signature value:int/0/int, default_value:int/0/int · returned str · level recorded 2026-09-26
fetch_recall eval_model.py ran MIT (permissive) · 7e2ff61e53717e1a · report fixture: signature metrics:dict/0/?, max_e:int/0/int · returned list · level recorded 2026-09-25
index_dataset dataset/npairs.py ran MIT (permissive) · b38d84edfb1e99ae · report fixture: signature dataset:MockDataset/0/? · returned dict · level recorded 2026-09-25
make_args experiment/base.py ran MIT (permissive) · cfde26759e9d9c42 · report fixture: signature dataset_roots:dict/0/? · returned dict · level recorded 2026-09-25
merge_clusters utils.py ran MIT (permissive) · 12d14d2613022a8b · report fixture: signature C:ndarray/1/int, gpu_ids:NoneType/0/? · returned ndarray · level recorded 2026-09-25
parse_bool in 9 papers experiment/margin_loss_resnet50.py ran MIT (permissive) · 88137d9a7fe8cbfe · report fixture: signature val:str/0/str · returned bool · level recorded 2026-09-26
parse_clustering_method experiment/margin_loss_resnet50.py ran MIT (permissive) · aa9272a8a0d334bf · report fixture: signature val:str/0/str · returned dict · level recorded 2026-09-26
run in 143 papers collect_env_info.py ran fingerprinted MIT (permissive) · 6f559a6380486ff9 · report fixture: signature command:str/0/str · returned tuple · level recorded 2026-09-25
run_and_parse_first_match in 15 papers collect_env_info.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · ab7aeddfa9e9fb2e · report fixture: signature run_lambda:callable/0/?, command:str/0/str, regex:str/0/str · returned str · level recorded 2026-09-25
run_and_read_all in 15 papers collect_env_info.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 84905132fbc263e3 · report fixture: signature run_lambda:callable/0/?, command:str/0/str · returned str · level recorded 2026-09-25
sample_from_class dataset/npairs.py ran MIT (permissive) · 8b0a5832a7d73092 · report fixture: signature images_by_class:dict/0/?, class_label_ind:int/0/int · returned Tensor · level recorded 2026-09-25
train_kmeans metriclearning/faissext.py ran MIT (permissive) · f9c73077030737d4 · report fixture: signature x:ndarray/2/float, num_clusters:int/0/int, gpu_ids:NoneType/0/?, niter:int/0/int, nredo:int/0/int, verbose:int/0/int, seed:int/0/int · returned ndarray · level recorded 2026-09-25
is_match in 6 papers browse_results.py unverified MIT (permissive) · d9a66474dd07a91d · report
preprocess_features in 20 papers metriclearning/faissext.py unverified MIT (permissive) · 38ac9dc17918d04e · report
reassign_clusters dataset/loader.py unverified MIT (permissive) · 93db13d8a6478b7c · report
reserve_faiss_gpu_memory metriclearning/faissext.py unverified MIT (permissive) · 094e0f4940c1d413 · report

Tasks

Image RetrievalMetric LearningRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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