Autor: |
Bara, Cristian-Paul, Ping, Qing, Mathur, Abhinav, Thattai, Govind, MV, Rohith, Sukhatme, Gaurav S. |
Rok vydání: |
2022 |
Předmět: |
|
Druh dokumentu: |
Working Paper |
Popis: |
We introduce a novel privacy-preserving methodology for performing Visual Question Answering on the edge. Our method constructs a symbolic representation of the visual scene, using a low-complexity computer vision model that jointly predicts classes, attributes and predicates. This symbolic representation is non-differentiable, which means it cannot be used to recover the original image, thereby keeping the original image private. Our proposed hybrid solution uses a vision model which is more than 25 times smaller than the current state-of-the-art (SOTA) vision models, and 100 times smaller than end-to-end SOTA VQA models. We report detailed error analysis and discuss the trade-offs of using a distilled vision model and a symbolic representation of the visual scene. |
Databáze: |
arXiv |
Externí odkaz: |
|