Adaptive Adversarial Latent Space for Novelty Detection
Novelty detection is a challenging task of identifying whether a new sample obeys to a known class. Note that the boundary between normal and novel is not clear enough in existing works, resulting from adequately reconstructing novel samples or crudely reconstructing normal samples. To tackle the ab...
Main Authors: | Bin Jiang, Fangqiang Xu, Yun Huang, Chao Yang, Wei Huang, Jun Xia |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9256333/ |
Similar Items
-
ADSAttack: An Adversarial Attack Algorithm via Searching Adversarial Distribution in Latent Space
by: Haobo Wang, et al.
Published: (2023-02-01) -
ABLAL: Adaptive Background Latent Space Adversarial Learning Algorithm for Hyperspectral Target Detection
by: Long Sun, et al.
Published: (2024-01-01) -
Associating Latent Representations With Cognitive Maps via Hyperspherical Space for Neural Population Spikes
by: Yicong Huang, et al.
Published: (2022-01-01) -
DefenseFea: An Input Transformation Feature Searching Algorithm Based Latent Space for Adversarial Defense
by: Pan Zhang, et al.
Published: (2024-02-01) -
Adversarial-based latent space alignment network for left atrial appendage segmentation in transesophageal echocardiography images
by: Xueli Zhu, et al.
Published: (2023-03-01)