Full-spectrum out-of-distribution detection
Existing out-of-distribution (OOD) detection literature clearly defines semantic shift as a sign of OOD but does not have a consensus over covariate shift. Samples experiencing covariate shift but not semantic shift from the in-distribution (ID) are either excluded from the test set or treated as OO...
Saved in:
Main Authors: | Yang, Jingkang, Zhou, Kaiyang, Liu, Ziwei |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/171361 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
POST-GDPR PRIVACY PRESERVATION IN ANDROID ECOSYSTEM
by: MARK MENG HUASONG
Published: (2024) -
Trustworthy and synergistic artificial intelligence for software engineering: Vision and roadmaps
by: LO, David
Published: (2023) -
Boosting adversarial training in safety-critical systems through boundary data selection
by: JIA, Yifan, et al.
Published: (2023) -
Towards robust explainability of deep neural networks against attribution attacks
by: Wang, Fan
Published: (2024) -
Directed trust and trustworthiness in a social network : an experimental investigation
by: Riyanto, Yohanes Eko, et al.
Published: (2019)