Generic Attention-model Explainability for Interpreting Bi-Modal and\n Encoder-Decoder Transformers

Hila Chefer(Tel Aviv University), Lior Wolf(Tel Aviv University), Shir Gur(Tel Aviv University)
arXiv (Cornell University)
March 29, 2021
10.48550/arxiv.2103.15679
Cited by 3

Related Papers

Face recognition in unconstrained videos with matched background similarity
|Unknown|2011|1.4k
Descriptor Based Methods in the Wild
|HAL (Le Centre pour la Communication Scientifique Directe)|2008|430
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
|ACM Transactions on Graphics|2023|384
Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics
|IEEE Transactions on Pattern Analysis and Machine Intelligence|2010|334
DeepFake Detection Based on Discrepancies Between Faces and Their Context
|IEEE Transactions on Pattern Analysis and Machine Intelligence|2021|296