Internet Archive Scholar
Filters
























1 Hit in 2.2 sec

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers [article]

Estelle Aflalo, Meng Du, Shao-Yen Tseng, Yongfei Liu, Chenfei Wu, Nan Duan, Vasudev Lal
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (9.7 MB)
https://web.archive.org/web/20220511063137/https://arxiv.org/pdf/2203.17247v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2022 pre-print
arXiv:2203.17247v1 fatcat:c67i3p5eyjhnxhn5ereoyxinde
VL-InterpreT is a task agnostic and integrated tool that (1) tracks a variety of statistics in attention heads throughout all layers for both vision and language components, (2) visualizes cross-modal  ...  To contribute to this quest, we propose VL-InterpreT, which provides novel interactive visualizations for interpreting the attentions and hidden representations in multimodal transformers.  ...  Conclusions and Future Directions In this paper we presented VL-InterpreT, an interactive visualization tool for interpreting vision-language transformers.  ... 
arXiv:2203.17247v2 fatcat:mcnvgrevcnf6plnyvikhjlx2ee
Open Access Multiple Versions
Citation

Estelle Aflalo, Meng Du, Shao-Yen Tseng, Yongfei Liu, Chenfei Wu, Nan Duan, Vasudev Lal. "VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers." arXiv (2022)