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 61–70 of 267 papers

TitleStatusHype
An Adaptable Deep Learning-Based Intrusion Detection System to Zero-Day Attacks—0
Detecting Unknown Attacks in IoT Environments: An Open Set Classifier for Enhanced Network Intrusion Detection—0
Dense outlier detection and open-set recognition based on training with noisy negative images—0
Boosting Deep Open World Recognition by Clustering—0
All Beings Are Equal in Open Set Recognition—0
Denoising Autoencoders for Overgeneralization in Neural Networks—0
Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and Angular Spaces—0
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning—0
Advanced Vision Transformers and Open-Set Learning for Robust Mosquito Classification: A Novel Approach to Entomological Studies—0
Deep Open-Set Recognition for Silicon Wafer Production Monitoring—0
Show:102550
← PrevPage 7 of 27Next →

No leaderboard results yet.