ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
This work addresses the challenge of generating accurate natural language answers from images and questions, which is important for applications in AI and human-computer interaction, though it appears incremental as it builds on existing attention mechanisms.
The authors tackled the visual question answering (VQA) problem by proposing ABC-CNN, an attention-based convolutional neural network that learns question-guided attention to focus on relevant image regions, achieving significant improvements over state-of-the-art methods on benchmark datasets like Toronto COCO-QA, DAQUAR, and VQA.
We propose a novel attention based deep learning architecture for visual question answering task (VQA). Given an image and an image related natural language question, VQA generates the natural language answer for the question. Generating the correct answers requires the model's attention to focus on the regions corresponding to the question, because different questions inquire about the attributes of different image regions. We introduce an attention based configurable convolutional neural network (ABC-CNN) to learn such question-guided attention. ABC-CNN determines an attention map for an image-question pair by convolving the image feature map with configurable convolutional kernels derived from the question's semantics. We evaluate the ABC-CNN architecture on three benchmark VQA datasets: Toronto COCO-QA, DAQUAR, and VQA dataset. ABC-CNN model achieves significant improvements over state-of-the-art methods on these datasets. The question-guided attention generated by ABC-CNN is also shown to reflect the regions that are highly relevant to the questions.