Target-oriented Multimodal Sentiment Classification with Counterfactual-enhanced Debiasing

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.

Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the CLIP's cross-modal association ability for image captioning, relying solely on textual information under unsupervised settings. However, not only does a modality gap exist between CLIP text and image features, but a discrepancy also arises between training and inference due to the unavailability of real-world images, which hinders the cross-modal alignment in text-only captioning. This paper proposes a novel method to address these issues by incorporating synthetic image-text pairs. A pre-trained text-to-image model is deployed to obtain images that correspond to textual data, and the pseudo features of generated images are optimized toward the real ones in the CLIP embedding space. Furthermore, textual information is gathered to represent image features, resulting in the image features with various semantics and the bridged modality gap. To unify training and inference, synthetic image features would serve as the training prefix for the language decoder, while real images are used for inference. Additionally, salient objects in images are detected as assistance to enhance the learning of modality alignment. Experimental results demonstrate that our method obtains the state-of-the-art performance on benchmark datasets.