CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification
This work addresses the challenge of leveraging multi-modal data for classification in domains like e-commerce and social media, offering incremental improvements over CLIP and state-of-the-art methods.
The paper tackles the problem of improving image-text classification by proposing CMA-CLIP, a framework that uses cross-modality attention to fuse information from images and text, resulting in an average 11.9% recall improvement on a retail dataset and a 5.5% accuracy gain on a fashion dataset compared to existing methods.
Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and recommendation. In this paper, we propose the Cross-Modality Attention Contrastive Language-Image Pre-training (CMA-CLIP), a new framework which unifies two types of cross-modality attentions, sequence-wise attention and modality-wise attention, to effectively fuse information from image and text pairs. The sequence-wise attention enables the framework to capture the fine-grained relationship between image patches and text tokens, while the modality-wise attention weighs each modality by its relevance to the downstream tasks. In addition, by adding task specific modality-wise attentions and multilayer perceptrons, our proposed framework is capable of performing multi-task classification with multi-modalities. We conduct experiments on a Major Retail Website Product Attribute (MRWPA) dataset and two public datasets, Food101 and Fashion-Gen. The results show that CMA-CLIP outperforms the pre-trained and fine-tuned CLIP by an average of 11.9% in recall at the same level of precision on the MRWPA dataset for multi-task classification. It also surpasses the state-of-the-art method on Fashion-Gen Dataset by 5.5% in accuracy and achieves competitive performance on Food101 Dataset. Through detailed ablation studies, we further demonstrate the effectiveness of both cross-modality attention modules and our method's robustness against noise in image and text inputs, which is a common challenge in practice.