Zero-shot out-of-distribution detection with outlier label exposure
As vision-language models like CLIP are widely applied to zero-shot tasks and gain remarkable performance on in-distribution (ID) data, detecting and rejecting out-of-distribution (OOD) inputs in the zero-shot setting have become crucial for ensuring the safety of using such models on the fly. Most...
Saved in:
Main Authors: | DING, Choubo, PANG, Guansong |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9789 https://ink.library.smu.edu.sg/context/sis_research/article/10789/viewcontent/2406.01170v1.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Modularized zero-shot VQA with pre-trained models
by: CAO, Rui, et al.
Published: (2023) -
Residual pattern learning for pixel-wise out-of-distribution detection in semantic segmentation
by: LIU, Y, et al.
Published: (2023) -
Improving out-of-distribution detection with disentangled foreground and background features
by: DING, Choubo, et al.
Published: (2024) -
AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection
by: ZHOU, Qihang, et al.
Published: (2024) -
Learning adversarial semantic embeddings for zero-shot recognition in open worlds
by: LI, Tianqi, et al.
Published: (2024)