Error Causal inference for Multi-Fusion models
Chengxi Li, Brent E. Harrison · 2021
In this paper, we propose an error causal inference method that could be used for finding dominant features for a faulty instance under a well-trained multi-modality input model, which could apply to any testing instance.We evaluate our method using a well-trained multimodalities stylish caption generation model and find those causal inferences that could provide us the insights for next step optimization.