Learning transferable negative prompts for out-of-distribution detection
Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To addre...
Saved in:
Main Authors: | LI, Tianqi, PANG, Guansong, BAI, Xiao, MIAO, Wenjun, ZHENG, Jin |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9759 https://ink.library.smu.edu.sg/context/sis_research/article/10759/viewcontent/2404.03248v1.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Alternate form reliability of the PPVT-III in 100 ESL university students
by: Hilton, Laurence M.
Published: (2014) -
Open-vocabulary object detection via debiased curriculum self-training
by: Zhang, Hanlue, et al.
Published: (2024) -
Simple image-level classification improves open-vocabulary object detection
by: FANG, Ruohuan, et al.
Published: (2024) -
Repeated Exposure to Vocabulary Websites and Academic Vocabulary Retention by University Students in Japan
by: Mirador, Josephine, et al.
Published: (2022) -
The validity of and the test anxiety produced by rational cloze test as a test of vocabulary
by: Nurhuda Benjama
Published: (2017)