SOURCE-LINKED INTELLIGENCE

Counterfactual Reasoning for Robust Visual Question Answering

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to language bias. Although counterfactual learning has shown promise, existing methods can be improved to better guide attention toward causal evidence and strengthen feature discrimination. To address this, we propose a novel training framework that enhances counterfactual contrastive learning for VQA. Our framework introduces three key contributions: (1) a three-stage curriculum for stable multi-objective optimization, (2) an enhance

Read original source ↗ Open in workspace

recordType

paper

region

Global