Pith. sign in

REVIEW 4 cited by

Open-World Semi-Supervised Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.03526 v3 pith:KCQMPUE3 submitted 2021-02-06 cs.LG cs.CV

classification cs.LGcs.CV
keywords classesnoveldatalearningseenorcasemi-supervisedtest
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data. However, this assumption rarely holds for data in-the-wild, where instances belonging to novel classes may appear at testing time. Here, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data. In this novel setting, the goal is to solve the class distribution mismatch between labeled and unlabeled data, where at the test time every input instance either needs to be classified into one of the existing classes or a new unseen class needs to be initialized. To tackle this challenging problem, we propose ORCA, an end-to-end deep learning approach that introduces uncertainty adaptive margin mechanism to circumvent the bias towards seen classes caused by learning discriminative features for seen classes faster than for the novel classes. In this way, ORCA reduces the gap between intra-class variance of seen with respect to novel classes. Experiments on image classification datasets and a single-cell annotation dataset demonstrate that ORCA consistently outperforms alternative baselines, achieving 25% improvement on seen and 96% improvement on novel classes of the ImageNet dataset.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MedXplore: Towards Reliable and Unbiased Generalized Category Discovery in Medical Imaging

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A frequency-based attention module plus adaptive margins raises generalized category discovery accuracy on four medical imaging benchmarks by an average of 8.5 points over prior methods.

  2. Explainable Novel Category Discovery in Semantic Concept Space

    cs.CV 2026-07 conditional novelty 6.0 of 10

    xNCD routes novel category discovery through a CLIP-aligned concept bottleneck, matching strong NCD baselines while producing intrinsic cluster- and instance-level concept explanations.

  3. Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement

    cs.CV 2025-07 conditional novelty 6.0 of 10

    APL improves fine-grained Generalized Category Discovery by learning shared, correspondable object-part features with an all-min contrastive loss, replacing the CLS token and gaining 2 to 6 accuracy points over SimGCD...

  4. Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clustering

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A prototype-learning pipeline with an extra 'unknown' anchor discovers and clusters novel hyperspectral classes under few-shot supervision.

Pith tools