Papers › OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

5 Jul 2022arXiv:2207.02261archive 2025-07-28

Mamshad Nayeem Rizve, Navid Kardan, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while relying on a small set of labeled data. One common assumption in most SSL methods is that the labeled and unlabeled data are from the same data distribution. However, this is hardly the case in many real-world scenarios, which limits their applicability. In this work, instead, we attempt to solve the challenging open-world SSL problem that does not make such an assumption. In the open-world SSL problem, the objective is to recognize samples of known classes, and simultaneously detect and cluster samples belonging to novel classes present in unlabeled data. This work introduces OpenLDN that utilizes a pairwise similarity loss to discover novel classes. Using a bi-level optimization rule this pairwise similarity loss exploits the information available in the labeled set to implicitly cluster novel class samples, while simultaneously recognizing samples from known classes. After discovering novel classes, OpenLDN transforms the open-world SSL problem into a standard SSL problem to achieve additional performance gains using existing SSL methods. Our extensive experiments demonstrate that OpenLDN outperforms the current state-of-the-art methods on multiple popular classification benchmarks while providing a better accuracy/training time trade-off.

Paper PDF Code Code 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="2207.02261")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract.

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

nayeemrizve/openldn 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

1 sample harvested; 1 ran; 1 honoured the contract we drafted; 0 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 · honoured contract

Licence: 0 of the 1 sample 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 nayeemrizve/OpenLDN. “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.

symmetric_mse_loss nayeemrizve/OpenLDN/base/losses/losses.py official repository ran · honoured contract fingerprinted MIT (permissive) · 829b0a3dadf8bc76 · report

Tasks

Open-World Semi-Supervised Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN (ResNet-18)	All accuracy (10% Labeled)	92.8	#1 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN (ResNet-18)	All accuracy (50% Labeled)	95.4	#1 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN (ResNet-18)	Novel accuracy (10% Labeled)	93.2	#1 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN (ResNet-18)	Novel accuracy (50% Labeled)	95.1	#1 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN (ResNet-18)	Seen accuracy (10% Labeled)	92.4	#1 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN (ResNet-18)	Seen accuracy (50% Labeled)	95.7	#1 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-100	OpenLDN (ResNet-18)	All accuracy (10% Labeled)	47.7	#2 of 3	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-100	OpenLDN (ResNet-18)	All accuracy (50% Labeled)	60.1	#2 of 3	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-100	OpenLDN (ResNet-18)	Novel accuracy (10% Labeled)	40.0	#2 of 3	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-100	OpenLDN (ResNet-18)	Novel accuracy (50% Labeled)	46.8	#2 of 3	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-100	OpenLDN (ResNet-18)	Seen accuracy (10% Labeled)	55.0	#2 of 3	Archive leaderboard	report
Open-World Semi-Supervised Learning	CIFAR-100	OpenLDN (ResNet-18)	Seen accuracy (50% Labeled)	73.5	#2 of 3	Archive leaderboard	report
Open-World Semi-Supervised Learning	ImageNet-100 (TEMI Split)	OpenLDN (ResNet-50)	All accuracy (50% Labeled)	79.1	#3 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	ImageNet-100 (TEMI Split)	OpenLDN (ResNet-50)	Novel accuracy (50% Labeled)	68.6	#3 of 5	Archive leaderboard	report
Open-World Semi-Supervised Learning	ImageNet-100 (TEMI Split)	OpenLDN (ResNet-50)	Seen accuracy (50% Labeled)	89.6	#3 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