Towards unbiased visual emotion recognition via causal intervention
Although much progress has been made in visual emotion recognition, researchers have realized that modern deep networks tend to exploit dataset characteristics to learn spurious statistical associations between the input and the target. Such dataset characteristics are usually treated as dataset bia...
Saved in:
Main Authors: | Chen, Yuedong, Yang, Xu, Cham, Tat-Jen, Cai, Jianfei |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172660 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Causal interventional training for image recognition
by: QIN, Wei, et al.
Published: (2023) -
Causal attention for unbiased visual recognition
by: WANG, Tan, et al.
Published: (2021) -
Causal classification of spatiotemporal quantum correlations in the absence of active interventions
by: Song, Min Jeong
Published: (2024) -
Sem2NeRF: converting single-view semantic masks to neural radiance fields
by: Chen, Yuedong, et al.
Published: (2023) -
Towards unbiased visual language reasoning and consistent segmentation
by: Huang, Jianqiang
Published: (2023)