ASCL: Adaptive self-supervised counterfactual learning for robust visual question answering

Xinyao Shu, Shiyang Yan, Xu Yang, Ziheng Wu, Zhongfeng Chen, Zhenyu Lu

Abstract: Highlights•A feature selection method mines the intrinsic information of samples.•A novel learnable adaptive method for feature selection.•A counterfactual learning method uses causal inference to mitigate language bias.•An adaptive contrastive loss learning method to automatically adjust the distance.