Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval
This work addresses the challenge of fine-grained cross-modal alignment in speech-image retrieval, offering an incremental improvement over existing techniques.
The paper tackles the problem of aligning speech and image for retrieval by introducing a cross-modal denoising training paradigm, resulting in a 2.0% improvement in mean R@1 on Flickr8k and 1.7% on SpokenCOCO compared to state-of-the-art methods.
The success of speech-image retrieval relies on establishing an effective alignment between speech and image. Existing methods often model cross-modal interaction through simple cosine similarity of the global feature of each modality, which fall short in capturing fine-grained details within modalities. To address this issue, we introduce an effective framework and a novel learning task named cross-modal denoising (CMD) to enhance cross-modal interaction to achieve finer-level cross-modal alignment. Specifically, CMD is a denoising task designed to reconstruct semantic features from noisy features within one modality by interacting features from another modality. Notably, CMD operates exclusively during model training and can be removed during inference without adding extra inference time. The experimental results demonstrate that our framework outperforms the state-of-the-art method by 2.0% in mean R@1 on the Flickr8k dataset and by 1.7% in mean R@1 on the SpokenCOCO dataset for the speech-image retrieval tasks, respectively. These experimental results validate the efficiency and effectiveness of our framework.