Papers › Generalized Category Discovery

Generalized Category Discovery

7 Jan 2022CVPR 2022 1arXiv:2201.02609archive 2025-07-28

Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

In this paper, we consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled classes or from novel ones. Existing recognition methods are not able to deal with this setting, because they make several restrictive assumptions, such as the unlabelled instances only coming from known - or unknown - classes, and the number of unknown classes being known a-priori. We address the more unconstrained setting, naming it 'Generalized Category Discovery', and challenge all these assumptions. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. Next, we propose the use of vision transformers with contrastive representation learning for this open-world setting. We then introduce a simple yet effective semi-supervised k-means method to cluster the unlabelled data into seen and unseen classes automatically, substantially outperforming the baselines. Finally, we also propose a new approach to estimate the number of classes in the unlabelled data. We thoroughly evaluate our approach on public datasets for generic object classification and on fine-grained datasets, leveraging the recent Semantic Shift Benchmark suite. Project page at https://www.robots.ox.ac.uk/~vgg/research/gcd

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 11 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 7 ran (3 with no instrument failure; 4 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

sgvaze/generalized-category-discovery officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 7 ran (4 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

11 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 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.

1ran · our draft was wrong
3ran; the contract check could not run
3ran
4unverified

Licence: 2 of the 11 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 sgvaze/generalized-category-discovery. “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.

sgvaze/generalized-category-discovery official repository 11 samples, 7 ran (4 instrument-failed) · 4 unverified
cluster_acc in 33 papers project_utils/cluster_utils.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 569a0b5d2369b072 · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int, return_ind:bool/0/bool · returned float64 · level recorded 2026-09-26
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
models/vision_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 55120f2026b56aa2 · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded, date not recorded
evaluate_clustering in 6 papers project_utils/cluster_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 15d2b95b53f6db9a · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int · returned tuple · level recorded 2026-09-24
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
methods/clustering/faster_mix_k_means_pytorch.py ran MIT (permissive) · 980dd2e8fa24f9da · report fixture: signature data1:Tensor/2/float, data2:Tensor/2/float, batch_size:NoneType/0/? · returned Tensor · level recorded 2026-09-26
purity_score in 10 papers project_utils/cluster_utils.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 1645ca2fb55ce1f8 · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int · returned float64 · level recorded 2026-09-24
strip_state_dict in 5 papers project_utils/general_utils.py ran MIT (permissive) · bc2c748ee9fffddf · report fixture: signature state_dict:dict/0/?, strip_key:str/0/str · returned dict · level recorded 2026-09-24
transform_moco_state_dict in 5 papers project_utils/general_utils.py ran MIT (permissive) · 443a6ab0aca3d0e3 · report fixture: signature obj:dict/0/?, num_classes:int/0/int · returned dict · level recorded 2026-09-24
get_dino_head_weights project_utils/general_utils.py unverified MIT (permissive) · aacf96bb3684f3d0 · report
info_nce_logits in 15 papers methods/contrastive_training/contrastive_training.py unverified MIT (permissive) · 77f9f4c0ee87724e · report
vit_small in 33 papers models/vision_transformer.py unverified MIT (permissive) · 995a10f898196998 · report
vit_tiny in 40 papers models/vision_transformer.py unverified MIT (permissive) · 996780ba4be89ba3 · report

Tasks

Fine-Grained Visual RecognitionOpen-World Semi-Supervised LearningRepresentation Learning

Datasets

Introduced by this paper, per the archive.

ImageNet-100 (GCD split)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-World Semi-Supervised Learning CIFAR-10 GCD (ViT-B-16) All accuracy (50% Labeled) 91.5 #5 of 5 Archive leaderboard report
Open-World Semi-Supervised Learning CIFAR-10 GCD (ViT-B-16) Novel accuracy (50% Labeled) 88.2 #5 of 5 Archive leaderboard report
Open-World Semi-Supervised Learning CIFAR-10 GCD (ViT-B-16) Seen accuracy (50% Labeled) 97.9 #5 of 5 Archive leaderboard report
Open-World Semi-Supervised Learning ImageNet-100 (TEMI Split) GCD (ViT-B-16) All accuracy (50% Labeled) 74.1 #4 of 5 Archive leaderboard report
Open-World Semi-Supervised Learning ImageNet-100 (TEMI Split) GCD (ViT-B-16) Novel accuracy (50% Labeled) 66.3 #4 of 5 Archive leaderboard report
Open-World Semi-Supervised Learning ImageNet-100 (TEMI Split) GCD (ViT-B-16) Seen accuracy (50% Labeled) 89.8 #4 of 5 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.

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