About: P-ODN: Prototype based Open Deep Network for Open Set Recognition

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: P-ODN: Prototype based Open Deep Network for Open Set Recognition Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
title	P-ODN: Prototype based Open Deep Network for Open Set Recognition
Creator	Files, Journal Of L A T E X Class,
source	ArXiv
abstract	Most of the existing recognition algorithms are proposed for closed set scenarios, where all categories are known beforehand. However, in practice, recognition is essentially an open set problem. There are categories we know called%22knowns%22, and there are more we do not know called%22unknowns%22. Enumerating all categories beforehand is never possible, consequently it is infeasible to prepare sufficient training samples for those unknowns. Applying closed set recognition methods will naturally lead to unseen-category errors. To address this problem, we propose the prototype based Open Deep Network (P-ODN) for open set recognition tasks. Specifically, we introduce prototype learning into open set recognition. Prototypes and prototype radiuses are trained jointly to guide a CNN network to derive more discriminative features. Then P-ODN detects the unknowns by applying a multi-class triplet thresholding method based on the distance metric between features and prototypes. Manual labeling the unknowns which are detected in the previous process as new categories. Predictors for new categories are added to the classification layer to%22open%22the deep neural networks to incorporate new categories dynamically. The weights of new predictors are initialized exquisitely by applying a distances based algorithm to transfer the learned knowledge. Consequently, this initialization method speed up the fine-tuning process and reduce the samples needed to train new predictors. Extensive experiments show that P-ODN can effectively detect unknowns and needs only few samples with human intervention to recognize a new category. In the real world scenarios, our method achieves state-of-the-art performance on the UCF11, UCF50, UCF101 and HMDB51 datasets.
has issue date	2019-05-06(xsd:dateTime)
has license	arxiv
sha1sum (hex)	a331c08cf6286d7a95a9837c3d9b8586b7f8e9ff
resource representing a document's title	P-ODN: Prototype based Open Deep Network for Open Set Recognition
resource representing a document's body	covid:a331c08cf6286d7a95a9837c3d9b8586b7f8e9ff#body_text
is schema:about of	named entity 'closed set' named entity 'initialized' named entity 'CNN' named entity 'Most' named entity 'algorithms' »more»

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software