Open-Set Recognition Model Based on Negative-Class Sample Feature Enhancement Learning Algorithm
In order to solve the problem that the F1-measure value and the AUROC value of some classical open-set classifier methods do not exceed 40% in high-openness scenarios, this paper proposes an algorithm combining negative-class feature enhancement learning and a Weibull distribution based on an extrem...
Main Authors: | Guowei Yang, Shijie Zhou, Minghua Wan |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/10/24/4725 |
Similar Items
-
Towards Knowledge Uncertainty Estimation for Open Set Recognition
by: Catarina Pires, et al.
Published: (2020-10-01) -
Open Set Recognition With Dissimilarity Weight for Unknown Attack Detection
by: Gun-Yoon Shin, et al.
Published: (2023-01-01) -
CAMV: Class Activation Mapping Value Towards Open Set Fine-Grained Recognition
by: Wei Dai, et al.
Published: (2021-01-01) -
Open-Set Specific Emitter Identification Based on Prototypical Networks and Extreme Value Theory
by: Chunsheng Wang, et al.
Published: (2023-03-01) -
Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery
by: Chloe Amanda Game, et al.
Published: (2023-03-01)