Bridging Modality Gap for Visual Grounding with Effecitve Cross-modal Distillation
This addresses the problem of multi-modal reasoning for researchers in computer vision and NLP, but it is incremental as it builds on existing pre-trained models.
The paper tackles the modality gap between visual and language features in visual grounding by proposing a cross-modal distillation framework, which improves performance over state-of-the-art methods on five datasets.
Visual grounding aims to align visual information of specific regions of images with corresponding natural language expressions. Current visual grounding methods leverage pre-trained visual and language backbones independently to obtain visual features and linguistic features. Although these two types of features are then fused through elaborately designed networks, the heterogeneity of the features renders them unsuitable for multi-modal reasoning. This problem arises from the domain gap between the single-modal pre-training backbones used in current visual grounding methods, which can hardly be bridged by the traditional end-to-end training method. To alleviate this, our work proposes an Empowering Pre-trained Model for Visual Grounding (EpmVG) framework, which distills a multimodal pre-trained model to guide the visual grounding task. EpmVG relies on a novel cross-modal distillation mechanism that can effectively introduce the consistency information of images and texts from the pre-trained model, reducing the domain gap in the backbone networks, and thereby improving the performance of the model in the visual grounding task. Extensive experiments have been conducted on five conventionally used datasets, and the results demonstrate that our method achieves better performance than state-of-the-art methods.