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 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="2201.02609")

Code

Syntology Ran 5 of 11 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sgvaze/generalized-category-discovery officialmentioned in papermentioned on GitHubpytorchMIT 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; 5 ran; 0 honoured the contract we drafted; 6 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.

1ran · fixture could not drive it
4ran
6unverified

Licence: 0 of the 11 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 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. “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.

drop_path sgvaze/generalized-category-discovery/models/vision_transformer.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 55120f2026b56aa2 · report
evaluate_clustering sgvaze/generalized-category-discovery/project_utils/cluster_utils.py official repository ran fingerprinted MIT (permissive) · 15d2b95b53f6db9a · report
purity_score sgvaze/generalized-category-discovery/project_utils/cluster_utils.py official repository ran fingerprinted MIT (permissive) · 1645ca2fb55ce1f8 · report
strip_state_dict sgvaze/generalized-category-discovery/project_utils/general_utils.py official repository ran MIT (permissive) · bc2c748ee9fffddf · report
transform_moco_state_dict sgvaze/generalized-category-discovery/project_utils/general_utils.py official repository ran MIT (permissive) · 443a6ab0aca3d0e3 · report
cluster_acc sgvaze/generalized-category-discovery/project_utils/cluster_utils.py official repository unverified MIT (permissive) · 569a0b5d2369b072 · report
get_dino_head_weights sgvaze/generalized-category-discovery/project_utils/general_utils.py official repository unverified MIT (permissive) · aacf96bb3684f3d0 · report
info_nce_logits sgvaze/generalized-category-discovery/methods/contrastive_training/contrastive_training.py official repository unverified MIT (permissive) · 77f9f4c0ee87724e · report
pairwise_distance sgvaze/generalized-category-discovery/methods/clustering/faster_mix_k_means_pytorch.py official repository unverified MIT (permissive) · 980dd2e8fa24f9da · report
vit_small sgvaze/generalized-category-discovery/models/vision_transformer.py official repository unverified MIT (permissive) · 995a10f898196998 · report
vit_tiny sgvaze/generalized-category-discovery/models/vision_transformer.py official repository 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