Resumen
In this paper, we propose an error causal inference method that could be used for finding dominant features for a faulty instance under a well-trained multi-modality input model, which could apply to any testing instance. We evaluate our method using a well-trained multimodalities stylish caption generation model and find those causal inferences that could provide us the insights for next step optimization.
| Idioma original | English |
|---|---|
| Título de la publicación alojada | 2nd Workshop on Advances in Language and Vision Research, ALVR 2021 - Proceedings |
| Editores | Xin Wang, Ronghang Hu, Drew Hudson, Tsu-Jui Fu, Marcus Rohrbach, Daniel Fried |
| Páginas | 11-15 |
| Número de páginas | 5 |
| ISBN (versión digital) | 9781954085374 |
| Estado | Published - 2021 |
| Evento | 2nd Workshop on Advances in Language and Vision Research, ALVR 2021 - Atlanta, United States Duración: jun 11 2021 → … |
Serie de la publicación
| Nombre | 2nd Workshop on Advances in Language and Vision Research, ALVR 2021 - Proceedings |
|---|
Conference
| Conference | 2nd Workshop on Advances in Language and Vision Research, ALVR 2021 |
|---|---|
| País/Territorio | United States |
| Ciudad | Atlanta |
| Período | 6/11/21 → … |
Nota bibliográfica
Publisher Copyright:©2021 Association for Computational Linguistics
ASJC Scopus subject areas
- Computer Science Applications
- Software
- Linguistics and Language
- Language and Linguistics
- Ophthalmology
Huella
Profundice en los temas de investigación de 'Error Causal inference for Multi-Fusion models'. En conjunto forman una huella única.Citar esto
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver