A Transformer-based Cross-modal Fusion Model with Adversarial Training for VQA Challenge 2021
This work addresses VQA performance for AI systems, but it is incremental as it builds on existing models and strategies.
The paper tackled the problem of improving visual question answering (VQA) by proposing a transformer-based cross-modal fusion model with adversarial training, achieving 76.72% accuracy on the VQAv2 test-std set.
In this paper, inspired by the successes of visionlanguage pre-trained models and the benefits from training with adversarial attacks, we present a novel transformerbased cross-modal fusion modeling by incorporating the both notions for VQA challenge 2021. Specifically, the proposed model is on top of the architecture of VinVL model [19], and the adversarial training strategy [4] is applied to make the model robust and generalized. Moreover, two implementation tricks are also used in our system to obtain better results. The experiments demonstrate that the novel framework can achieve 76.72% on VQAv2 test-std set.