Stacked Attention Networks for Image Question Answering
This addresses the challenge of multi-step reasoning in image question answering, which is important for applications like visual assistants, but it is incremental as it builds on existing attention mechanisms.
The paper tackles the problem of answering natural language questions about images by proposing stacked attention networks (SANs) that perform multiple steps of reasoning to locate relevant visual regions, achieving significant improvements over previous state-of-the-art methods on four datasets.
This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query to search for the regions in an image that are related to the answer. We argue that image question answering (QA) often requires multiple steps of reasoning. Thus, we develop a multiple-layer SAN in which we query an image multiple times to infer the answer progressively. Experiments conducted on four image QA data sets demonstrate that the proposed SANs significantly outperform previous state-of-the-art approaches. The visualization of the attention layers illustrates the progress that the SAN locates the relevant visual clues that lead to the answer of the question layer-by-layer.