Papers › Learning to Cluster Faces via Confidence and Connectivity Estimation

Learning to Cluster Faces via Confidence and Connectivity Estimation

1 Apr 2020CVPR 2020 6arXiv:2004.00445archive 2025-07-28

Lei Yang, Dapeng Chen, Xiaohang Zhan, Rui Zhao, Chen Change Loy, Dahua Lin

Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance gain. However, they usually involve heuristic steps and require numerous overlapped subgraphs, severely restricting their accuracy and efficiency. In this paper, we propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs. Instead, we transform the clustering problem into two sub-problems. Specifically, two graph convolutional networks, named GCN-V and GCN-E, are designed to estimate the confidence of vertices and the connectivity of edges, respectively. With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters. Experiments on two large-scale benchmarks show that our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.

PaperPDFConference PDFCodeCode 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 15 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 2 ran (1 with no instrument failure; 1 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yl-1993/learn-to-cluster officialmentioned on GitHubpytorchMITSyntology: 12 samples, 9 ran (0 instrument-failed) · 3 unverified report
espectre/GCNs_on_imbalanced_datasets mentioned on GitHubpytorchSyntology: not harvested report
xiaoxiong74/face-cluster-by-infomap mentioned on GitHubSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 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

15 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 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 has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
9ran
4unverified

Licence: 3 of the 15 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

yl-1993/learn-to-cluster official repository 12 samples, 9 ran (0 instrument-failed) · 3 unverified
batch_processor dsgcn/train_cluster_det.py ran MIT (permissive) · d1e42462952f4277 · report fixture: signature model:callable/0/?, data:list/1/Tensor, train_mode:bool/0/bool · returned dict · level recorded 2026-09-25
calculate_symmetric_dist_row baseline/aro.py ran MIT (permissive) · 61d9d93a5700b210 · report fixture: signature nbrs:ndarray/2/int, nn_lookup:dict/0/?, row_no:int/0/int · returned ndarray · level recorded 2026-09-25
compute_avg_size proposals/stat_cluster.py ran fingerprinted MIT (permissive) · 671fbde87ae2e949 · report fixture: signature lst:list/1/int · returned float · level recorded 2026-09-25
coverage in 7 papers proposals/stat_cluster.py ran MIT (permissive) · f011ce5a79dd2638 · report fixture: signature s:set/0/?, size:int/0/int · returned float · level recorded 2026-09-25
create_neighbor_lookup baseline/aro.py ran fingerprinted MIT (permissive) · 49ed6fe34473d065 · report fixture: signature nbrs:ndarray/2/int · returned dict · level recorded 2026-09-25
filter_clusters utils/misc_cluster.py ran MIT (permissive) · a8370c85b9562d48 · report fixture: signature clusters:list/1/list, min_size:int/0/int, max_size:int/0/int · returned list · level recorded 2026-09-25
get_cluster_idxs utils/misc_cluster.py ran MIT (permissive) · 60febb59c4639544 · report fixture: signature clusters:list/1/list, size:int/0/int · returned list · level recorded 2026-09-25
get_majority proposals/stat_cluster.py ran MIT (permissive) · a5cd7a9c6072f6ec · report fixture: signature lb2cnt:dict/0/? · returned tuple · level recorded 2026-09-25
mini_batch_kmeans baseline/sklearn_cluster.py ran MIT (permissive) · ce7e06b25832df77 · report fixture: signature feat:ndarray/2/float, n_clusters:int/0/int, batch_size:int/0/int · returned ndarray · level recorded 2026-09-25
build_index in 7 papers baseline/aro.py unverified MIT (permissive) · 2a4fdc4d0c86bc3b · report
kmeans in 38 papers baseline/sklearn_cluster.py unverified MIT (permissive) · fc332f32dc148ea5 · report
spectral baseline/sklearn_cluster.py unverified MIT (permissive) · 073c0bbb90ff55ad · report
xiaoxiong74/face-cluster-by-infomap community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
face-cluster-by-infomap.py ran · violated contract fingerprinted no licence file found · pointer only · 9e5b9ebb30a1dab5 · report fixture: signature vec:ndarray/2/float · returned ndarray · level recorded 2026-09-22
read_meta in 7 papers face-cluster-by-infomap.py ran · our draft was wrong no licence file found · pointer only · b91ea1291400178a · report fixture: signature fn_meta:str/0/str, start_pos:int/0/int, verbose:bool/0/bool · returned tuple · level recorded 2026-09-22
intdict2ndarray face-cluster-by-infomap.py unverified no licence file found · pointer only · 7fd66383242447ba · report

Tasks

ClusteringConnectivity EstimationFace ClusteringRetrieval

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