Papers
arxiv:2609.16567

Counterfactual Reasoning for Robust Visual Question Answering

Published on Sep 15
Authors:
,
,

Abstract

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 enhanced Batch-Contrastive loss for more discriminative feature learning, and (3) two novel regularizers, Answer-Contrastive (AC) loss to refine the prediction space and Gradient-Discrepancy (GD) loss to enforce causal visual grounding. Our model achieves a competitive accuracy of 61.64% on the bias-sensitive VQA-CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, yielding a small generalization gap of 1.16%. This demonstrates a strong balance between OOD robustness and in-distribution performance.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.16567
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.16567 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.16567 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.16567 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.