Papers › Open-Set Recognition: a Good Closed-Set Classifier is All You Need?

Open-Set Recognition: a Good Closed-Set Classifier is All You Need?

12 Oct 2021ICLR 2022 4arXiv:2110.06207archive 2025-07-28

Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

The ability to identify whether or not a test sample belongs to one of the semantic classes in a classifier's training set is critical to practical deployment of the model. This task is termed open-set recognition (OSR) and has received significant attention in recent years. In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes. We find that this relationship holds across loss objectives and architectures, and further demonstrate the trend both on the standard OSR benchmarks as well as on a large-scale ImageNet evaluation. Second, we use this correlation to boost the performance of a maximum logit score OSR 'baseline' by improving its closed-set accuracy, and with this strong baseline achieve state-of-the-art on a number of OSR benchmarks. Similarly, we boost the performance of the existing state-of-the-art method by improving its closed-set accuracy, but the resulting discrepancy with the strong baseline is marginal. Our third contribution is to present the 'Semantic Shift Benchmark' (SSB), which better respects the task of detecting semantic novelty, in contrast to other forms of distribution shift also considered in related sub-fields, such as out-of-distribution detection. On this new evaluation, we again demonstrate that there is negligible difference between the strong baseline and the existing state-of-the-art. Project Page: https://www.robots.ox.ac.uk/~vgg/research/osr/

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 17 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 15 ran (12 with no instrument failure; 3 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. 1 of the 15 samples that ran has no recorded date.

sgvaze/osr_closed_set_all_you_need officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 15 ran (3 instrument-failed) · 2 unverified report
t9liverpool/OpenMix mentioned on GitHubpytorchSyntology: not harvested 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 2 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 · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
11ran
2unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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/osr_closed_set_all_you_need. “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/osr_closed_set_all_you_need official repository 17 samples, 15 ran (3 instrument-failed) · 2 unverified
get_mean_lr methods/ARPL/osr.py ran · honoured contract MIT (permissive) · c62a45794431e9b7 · report fixture: signature optimizer:SGD/0/? · returned float · level recorded, date not recorded
Discriminator32 in 6 papers methods/ARPL/arpl_models/gan.py ran MIT (permissive) · 3cce4936256bdc33 · report fixture: signature n_gpu:int/0/int, nc:int/0/int, ndf:int/0/int · returned _netD32 · level recorded 2026-09-25
Generator in 95 papers methods/ARPL/arpl_models/gan.py ran MIT (permissive) · 1a6a50a611f464f9 · report fixture: signature n_gpu:int/0/int, nz:int/0/int, ngf:int/0/int, nc:int/0/int · returned _netG · level recorded 2026-09-24
Generator32 in 6 papers methods/ARPL/arpl_models/gan.py ran MIT (permissive) · 8c24b39fc0eecb58 · report fixture: signature n_gpu:int/0/int, nz:int/0/int, ngf:int/0/int, nc:int/0/int · returned _netG32 · level recorded 2026-09-24
drop_connect in 73 papers
census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
models/miscel_utils.py ran; the contract check could not run (RAISES) MIT (permissive) · d3319e3d34ca90ca · report fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_file in 18 papers utils/logfile_parser.py ran MIT (permissive) · 142c0ce9982cbf82 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
get_optimizer in 228 papers methods/ARPL/osr.py ran MIT (permissive) · ed5db303ab193775 · report fixture: signature args:Args/0/?, params_list:list/1/Tensor · returned SGD · level recorded 2026-09-24
get_scheduler in 122 papers utils/schedulers.py ran MIT (permissive) · 8d59d5daedcdf3f8 · report fixture: signature optimizer:SGD/0/?, args:Args/0/? · returned CosineAnnealingWarmupRestarts_New · level recorded 2026-09-25
load_networks methods/ARPL/arpl_utils.py ran MIT (permissive) · a811aa6eac543d8f · report fixture: signature networks:callable/0/?, result_dir:str/0/str, name:str/0/str, loss:str/0/str, criterion:callable/0/? · returned tuple · level recorded 2026-09-24
round_filters in 47 papers models/miscel_utils.py ran · our draft was wrong MIT (permissive) · f15a49337e69e937 · report fixture: signature filters:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22
round_repeats in 39 papers models/miscel_utils.py ran · our draft was wrong MIT (permissive) · dbc0ca08d119a5a0 · report fixture: signature repeats:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22
strip_state_dict in 5 papers utils/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 models/model_utils.py ran MIT (permissive) · 443a6ab0aca3d0e3 · report fixture: signature obj:dict/0/?, num_classes:int/0/int · returned dict · level recorded 2026-09-24
transform_moco_state_dict_arpl_cs models/model_utils.py ran MIT (permissive) · d040dabdf943f132 · report fixture: signature obj:dict/0/?, num_classes:int/0/int · returned dict · level recorded 2026-09-24
transform_moco_state_dict_places models/model_utils.py ran MIT (permissive) · 1219ffd1eb121b9e · report fixture: signature obj:dict/0/?, num_classes:int/0/int, supervised:bool/0/bool · returned dict · level recorded 2026-09-24
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils/utils.py unverified MIT (permissive) here; the stored copy is pointer only · 913d82af53065418 · report
init_experiment in 9 papers utils/utils.py unverified MIT (permissive) · 7767f8e34fb9f60c · report

Tasks

AllOpen Set LearningOut-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection CIFAR-100 vs CIFAR-10 Maximum Logit Score (MLS) AUROC 83.2 #10 of 14 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.

Methods

Test

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