Papers Open Set Learning

“Open Set Learning” 태그가 달린 논문 267편 · 필터 해제

Polyhedral Conic Classifiers for Visual Object Detection and Classification

2017-07-01 · CVPR 2017 7 · Hakan Cevikalp, Bill Triggs

We propose a family of quasi-linear discriminants that outperform current large-margin methods in sliding window visual object detection and open set recognition tasks. In these tasks the classification problems are b…

Classification General Classification Object object-detection+2

Vocabulary-informed Extreme Value Learning

2017-05-28 · Yanwei Fu, Hanze Dong, Yu-feng Ma, Zhengjun Zhang 외

The novel unseen classes can be formulated as the extreme values of known classes. This inspired the recent works on open-set recognition \cite{Scheirer_2013_TPAMI,Scheirer_2014_TPAMIb,EVM}, which however can have no way…

Open Set Learning

Sparse Representation-based Open Set Recognition

2017-05-06 · He Zhang, Vishal M. Patel

We propose a generalized Sparse Representation- based Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training. The SRC algorithm uses class reconst…

Classification General Classification Open Set Learning Sparse Representation-based Classification+1

Specialized Support Vector Machines for Open-set Recognition

2016-06-13 · Pedro Ribeiro Mendes Júnior, Terrance E. Boult, Jacques Wainer, Anderson Rocha

Often, when dealing with real-world recognition problems, we do not need, and often cannot have, knowledge of the entire set of possible classes that might appear during operational testing. In such cases, we need to thi…

General Classification Open Set Learning Robust classification

Semi-supervised Vocabulary-informed Learning

2016-04-24 · CVPR 2016 6 · Yanwei Fu, Leonid Sigal

Despite significant progress in object categorization, in recent years, a number of important challenges remain, mainly, ability to learn from limited labeled data and ability to recognize object classes within large, po…

Object Categorization Open Set Learning Zero-Shot Learning

Towards Open Set Deep Networks

2015-11-19 · CVPR 2016 6 · Abhijit Bendale, Terrance Boult

Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate ima…

Open Set Learning

Toward an Efficient Multi-class Classification in an Open Universe

2015-11-02 · Wajdi Dhifli, Abdoulaye Baniré Diallo

Classification is a fundamental task in machine learning and data mining. Existing classification methods are designed to classify unknown instances within a set of previously known training classes. Such a classificatio…

Classification General Classification Multi-class Classification open-set classification+1