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 1–50 of 267 papers

TitleStatusHype
Open-Set Image Tagging with Multi-Grained Text SupervisionCode4
Towards Open Vocabulary Learning: A SurveyCode2
Open World Object Detection: A SurveyCode2
Open-Set Recognition: a Good Closed-Set Classifier is All You Need?Code1
Open-Set Likelihood Maximization for Few-Shot LearningCode1
Open-set recognition with long-tail sonar imagesCode1
Open-set Adversarial Defense with Clean-Adversarial Mutual LearningCode1
Learning Placeholders for Open-Set RecognitionCode1
Navigating Open Set Scenarios for Skeleton-based Action RecognitionCode1
Open-set Adversarial DefenseCode1
Generalized Out-of-Distribution Detection: A SurveyCode1
GDumb: A Simple Approach that Questions Our Progress in Continual LearningCode1
Open Set Recognition using Vision Transformer with an Additional Detection HeadCode1
HomOpt: A Homotopy-Based Hyperparameter Optimization MethodCode1
In or Out? Fixing ImageNet Out-of-Distribution Detection EvaluationCode1
Driver Anomaly Detection: A Dataset and Contrastive Learning ApproachCode1
Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open WorldsCode1
Learning Open Set Network with Discriminative Reciprocal PointsCode1
Exploring Diverse Representations for Open Set RecognitionCode1
Model-Agnostic Few-Shot Open-Set RecognitionCode1
OpenAUC: Towards AUC-Oriented Open-Set RecognitionCode1
OpenGCD: Assisting Open World Recognition with Generalized Category DiscoveryCode1
Few-shot Open-set Recognition by Transformation ConsistencyCode1
Few-Shot Open-Set Recognition using Meta-LearningCode1
A Unified Benchmark for the Unknown Detection Capability of Deep Neural NetworksCode1
A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future ChallengesCode1
GlanceNets: Interpretabile, Leak-proof Concept-based ModelsCode1
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background PriorsCode1
Glocal Energy-based Learning for Few-Shot Open-Set RecognitionCode1
Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity RecognitionCode1
DenseHybrid: Hybrid Anomaly Detection for Dense Open-set RecognitionCode1
Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting SystemsCode1
Difficulty-Aware Simulator for Open Set RecognitionCode1
Class Anchor Clustering: a Loss for Distance-based Open Set RecognitionCode1
Adversarial Motorial Prototype Framework for Open Set RecognitionCode1
Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and BenchmarksCode1
Domain Adaptive Few-Shot Open-Set LearningCode1
Learning Bounds for Open-Set LearningCode1
Adversarial Reciprocal Points Learning for Open Set RecognitionCode1
Evidential Deep Learning for Open Set Action RecognitionCode1
Conditional Gaussian Distribution Learning for Open Set RecognitionCode1
Conditional Variational Capsule Network for Open Set RecognitionCode1
OneRing: A Simple Method for Source-free Open-partial Domain AdaptationCode1
COOOL: Challenge Of Out-Of-Label A Novel Benchmark for Autonomous DrivingCode1
Counterfactual Zero-Shot and Open-Set Visual RecognitionCode1
OpenGAN: Open-Set Recognition via Open Data GenerationCode1
Large-Scale Long-Tailed Recognition in an Open WorldCode1
Fully Convolutional Open Set SegmentationCode1
Maximum Class Separation as Inductive Bias in One MatrixCode1
Open-Set Automatic Target RecognitionCode1
Show:102550
← PrevPage 1 of 6Next →

No leaderboard results yet.