Papers › Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

8 Feb 2022ICLR 2022 4arXiv:2202.03800archive 2025-07-28

Yaohua Wang, Yaobin Zhang, Fangyi Zhang, Ming Lin, Yuqi Zhang, Senzhang Wang, Xiuyu Sun

Face clustering has attracted rising research interest recently to take advantage of massive amounts of face images on the web. State-of-the-art performance has been achieved by Graph Convolutional Networks (GCN) due to their powerful representation capacity. However, existing GCN-based methods build face graphs mainly according to kNN relations in the feature space, which may lead to a lot of noise edges connecting two faces of different classes. The face features will be polluted when messages pass along these noise edges, thus degrading the performance of GCNs. In this paper, a novel algorithm named Ada-NETS is proposed to cluster faces by constructing clean graphs for GCNs. In Ada-NETS, each face is transformed to a new structure space, obtaining robust features by considering face features of the neighbour images. Then, an adaptive neighbour discovery strategy is proposed to determine a proper number of edges connecting to each face image. It significantly reduces the noise edges while maintaining the good ones to build a graph with clean yet rich edges for GCNs to cluster faces. Experiments on multiple public clustering datasets show that Ada-NETS significantly outperforms current state-of-the-art methods, proving its superiority and generalization. Code is available at https://github.com/damo-cv/Ada-NETS.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 2 repositories, 11 ran (11 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

damo-cv/ada-nets officialmentioned in paperpytorchMITSyntology: 14 samples, 11 ran (0 instrument-failed) · 3 unverified report
Thomas-wyh/Ada-NETS officialpytorchSyntology: 1 sample, 0 ran · 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; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 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.

11ran
4unverified

Licence: 0 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.

damo-cv/ada-nets official repository 14 samples, 11 ran (0 instrument-failed) · 3 unverified
batch_search tool/faiss_search.py ran MIT (permissive) · bb6e98a818ab83bb · report fixture: signature index:MockFaissIndex/0/?, query:ndarray/2/float, topk:int/0/int, bs:int/0/int, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
build_symmetric_adj AND/adjacency.py ran MIT (permissive) · b47e4da5605e550d · report fixture: signature adj:csr_matrix/2/float, self_loop:bool/0/bool · returned csr_matrix · level recorded 2026-09-24
clusters2labels GCN/cluster.py ran MIT (permissive) · 9cb5361facb80118 · report fixture: signature clusters:list/1/list, n_nodes:int/0/int · returned ndarray · level recorded 2026-09-24
filter_knns tool/knn.py ran MIT (permissive) · 960270dfb8856837 · report fixture: signature knns:list/1/tuple, k:int/0/int, th:float/0/float · returned tuple · level recorded 2026-09-24
gcn_v AND/net/gcn_v.py ran MIT (permissive) · f3041fc06ca7bbed · report fixture: signature feature_dim:int/0/int, nhid:int/0/int, nclass:int/0/int, dropout:float/0/float · returned GCN_V · level recorded 2026-09-24
get_neg_loss GCN/net/optim_modules.py ran MIT (permissive) · 72c104b3d72d0dd9 · report fixture: signature decision_mat:Tensor/2/float, label_mat:Tensor/2/bool, beta:float/0/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
get_pos_loss GCN/net/optim_modules.py ran MIT (permissive) · 9ee109079dbd413e · report fixture: signature decision_mat:Tensor/2/float, label_mat:Tensor/2/bool, beta:float/0/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
knns2ordered_nbrs tool/knn.py ran MIT (permissive) · 227696c1d71b8892 · report fixture: signature knns:ndarray/3/float, sort:bool/0/bool · returned tuple · level recorded 2026-09-24
row_normalize in 6 papers AND/adjacency.py ran MIT (permissive) · ce0784d592bd0d41 · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-24
sparse_mx_to_indices_values AND/adjacency.py ran MIT (permissive) · f73847ac9f20f56a · report fixture: signature sparse_mx:csr_matrix/2/float · returned tuple · level recorded 2026-09-24
sqeuclidean_pdist GCN/net/optim_modules.py ran fingerprinted MIT (permissive) · 6bd747fe350f9027 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
format in 9 papers GCN/cluster.py unverified MIT (permissive) · b49214d884be3833 · report
get_topK tool/max_Q_ind.py unverified MIT (permissive) · 020579fb712da25b · report
knns_recall tool/knn.py unverified MIT (permissive) · 6979c33355f8cd0a · report
Thomas-wyh/Ada-NETS official repository 1 sample, 0 ran · 1 unverified
get_Rstarset tool/struct_space.py unverified MIT (permissive) · 874120f76adf0d08 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Ada-NETS (graph method: Ada-NETS). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. get_Rstarset entry · level 0 · unverified · 874120f76adf0d08

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2202.03800") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringFace Clustering

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