Learning a Neural-network-based Representation for Open Set Recognition

02/12/2018
by   Mehadi Hassen, et al.
0

Open set recognition problems exist in many domains. For example in security, new malware classes emerge regularly; therefore malware classification systems need to identify instances from unknown classes in addition to discriminating between known classes. In this paper we present a neural network based representation for addressing the open set recognition problem. In this representation instances from the same class are close to each other while instances from different classes are further apart, resulting in statistically significant improvement when compared to other approaches on three datasets from two different domains.

READ FULL TEXT
research
06/26/2020

MMF: A loss extension for feature learning in open set recognition

Open set recognition (OSR) is the problem of classifying the known class...
research
11/20/2022

MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration

Open-set recognition refers to the problem in which classes that were no...
research
05/13/2022

Representation learning with function call graph transformations for malware open set recognition

Open set recognition (OSR) problem has been a challenge in many machine ...
research
05/02/2023

CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario

We study the challenging task of malware recognition on both known and n...
research
11/13/2018

Co-Representation Learning For Classification and Novel Class Detection via Deep Networks

Deep Neural Network (DNN) has been largely demonstrated to be effective ...
research
09/28/2022

Feature Decoupling in Self-supervised Representation Learning for Open Set Recognition

Assuming unknown classes could be present during classification, the ope...
research
09/27/2018

Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics

When performing data classification over a stream of continuously occurr...

Please sign up or login with your details

Forgot password? Click here to reset