Enhancing multi-modal fusion in visual dialog via sample debiasing and feature interaction

Chenyu Lu, Jun Yin, Hao Yang, Shiliang Sun

Abstract: Highlights•We propose a visual dialog model termed CS-PAF.•CS-PAF enhances fusion balance via counterfactual sample generation.•CS-PAF enhances fusion sufficiency by parallelly stacking fusion units.•Extensive experiments demonstrate the superiority of CS-PAF over other methods.