Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
This work addresses the challenge of integrating separate visual and textual components for improved grounding in vision-and-language applications, though it appears incremental as it builds on existing baseline models.
The paper tackled the problem of fine-grained image representation in vision-and-language tasks by aligning visual regions and textual concepts to create semantic-grounded representations, resulting in consistent performance boosts across image captioning and visual question answering tasks.
In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance. Most of the current systems incorporate visual features and textual concepts as a sketch of an image. However, plainly inferred representations are usually undesirable in that they are composed of separate components, the relations of which are elusive. In this work, we aim at representing an image with a set of integrated visual regions and corresponding textual concepts, reflecting certain semantics. To this end, we build the Mutual Iterative Attention (MIA) module, which integrates correlated visual features and textual concepts, respectively, by aligning the two modalities. We evaluate the proposed approach on two representative vision-and-language grounding tasks, i.e., image captioning and visual question answering. In both tasks, the semantic-grounded image representations consistently boost the performance of the baseline models under all metrics across the board. The results demonstrate that our approach is effective and generalizes well to a wide range of models for image-related applications. (The code is available at https://github.com/fenglinliu98/MIA)