Abstract
Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to consider dataset biases, in particular word-level contextual biases. This leads to spurious correlations between text features and output labels, impairing classification accuracy. In this paper, we introduce a novel counterfactual-enhanced debiasing framework to reduce such spurious correlations. Our framework incorporates a counterfactual data augmentation strategy that minimally alters sentiment-related causal features, generating detail-matched image-text samples to guide the model's attention toward content tied to sentiment. Furthermore, for learning robust features from counterfactual data and prompting model decisions, we introduce an adaptive debiasing contrastive learning mechanism, which effectively mitigates the influence of biased words. Experimental results on several benchmark datasets show that our proposed method outperforms state-of-the-art baselines.
Abstract (translated)
以目标为导向的多模态情感分类旨在从图像-文本对中预测特定目标的情感极性。尽管现有研究已经取得了竞争性的性能，但它们往往过度依赖于文本内容，并且未能考虑数据集中的偏差，尤其是词级别的上下文偏见。这导致了文本特征与输出标签之间的虚假相关性，从而损害了分类的准确性。在本文中，我们引入了一种新颖的反事实增强去偏框架，以减少此类虚假相关性。我们的框架结合了一个反事实数据扩充策略，该策略最小程度地修改情感相关的因果特征，并生成细节匹配的图像-文本样本，引导模型关注与情感内容相关的内容。此外，为了从反事实数据中学习稳健的功能并提示模型决策，我们引入了一种自适应去偏对比学习机制，这有效地减轻了有偏差单词的影响。在几个基准数据集上的实验结果表明，我们提出的方法优于现有的最先进基线方法。
URL
https://arxiv.org/abs/2509.09160
