VLStereoSet: A study of stereotypical bias in pre-trained vision-language models
In this paper we study how to measure stereotypical bias in pre-trained vision-language models. We leverage a recently released text-only dataset, StereoSet, which covers a wide range of stereotypical bias, and extend it into a vision-language probing dataset called VLStereoSet to measure stereotypi...
Saved in:
Main Authors: | ZHOU, Kankan, LAI, Yibin, JIANG, Jing |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7617 https://ink.library.smu.edu.sg/context/sis_research/article/8620/viewcontent/2022.aacl_main.40.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Position-guided text prompt for vision-language pre-training
by: WANG, Alex Jinpeng, et al.
Published: (2023) -
Using pre-trained models for vision-language understanding tasks
by: CAO, Rui
Published: (2024) -
Cross-thought for sentence encoder pre-training
by: WANG, Shuohang, et al.
Published: (2020) -
Enhancing visual grounding in vision-language pre-training with position-guided text prompts
by: WANG, Alex Jinpeng, et al.
Published: (2024) -
Injecting descriptive meta-information into pre-trained language models with hypernetworks
by: DUAN, Wenying, et al.
Published: (2021)