Self-supervised knowledge distillation in counterfactual learning for VQA

Yandong Bi, Huajie Jiang, Hanfu Zhang, Yongli Hu, Baocai Yin

Abstract: Highlights•We study the relations of factual and original samples in counterfactual learning.•We design a self-supervised knowledge distillation module to learn robust features.•Our method is model-agnostic, end-to-end trainable, and easy to implement.•Extensive experiments on three datasets show the effectiveness of our approach.