Deconfounded visual grounding
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial languagelocation association without visual reasoning, e.g., grounding any la...
Saved in:
Main Authors: | HUANG, Jianqiang, QIN, Yu, QI, Jiaxin, SUN, Qianru, ZHANG, Hanwang |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7484 https://ink.library.smu.edu.sg/context/sis_research/article/8487/viewcontent/19983_Article_Text_23996_1_2_20220628.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Visual Commonsense R-CNN
by: WANG, Tan, et al.
Published: (2020) -
Open-set domain adaptation by deconfounding domain gaps
by: ZHAO, Xin, et al.
Published: (2023) -
Reducing adaptation latency for multi-concept visual perception in outdoor environments
by: WIGNESS, Maggie, et al.
Published: (2016) -
Visual commonsense representation learning via causal inference
by: WANG, Tan, et al.
Published: (2020) -
Causal attention for unbiased visual recognition
by: WANG, Tan, et al.
Published: (2021)