SOTAVerified

Open Set Learning

Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. Open set learning (OSL) is a more challenging and realistic setting, where there exist test samples from the classes that are unseen during training. Open set recognition (OSR) is the sub-task of detecting test samples which do not come from the training.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 267 papers

TitleStatusHype
ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence AlignmentCode0
Disentangled representations of microscopy imagesCode0
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point CloudsCode0
Hyperbolic Dual Feature Augmentation for Open-Environment—0
Open-Set Semi-Supervised Learning for Long-Tailed Medical DatasetsCode0
Synthetic Non-stationary Data Streams for Recognition of the UnknownCode0
Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation—0
Malware families discovery via Open-Set Recognition on Android manifest permissions—0
Structure-based Anomaly Detection and Clustering—0
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background PriorsCode1
Open-Set Plankton Recognition—0
SphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning ModelsCode0
Open-Set Recognition of Novel Species in Biodiversity Monitoring—0
G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition—0
A Survey of Text Classification Under Class Distribution ShiftCode0
Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data—0
Cross-Rejective Open-Set SAR Image RegistrationCode0
Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain GeneralizationCode0
Robustness-enhanced Myoelectric Control with GAN-based Open-set RecognitionCode0
COOOL: Challenge Of Out-Of-Label A Novel Benchmark for Autonomous DrivingCode1
Unlocking Transfer Learning for Open-World Few-Shot Recognition—0
Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalization—0
Electromagnetic Scattering Kernel Guided Reciprocal Point Learning for SAR Open-Set Recognition—0
Data-Driven Hierarchical Open Set Recognition—0
Deep Learning for Leopard Individual Identification: An Adaptive Angular Margin ApproachCode0
Show:102550
← PrevPage 1 of 11Next →

No leaderboard results yet.