Differential Attention for Visual Question Answering
In this paper we aim to answer questions based on images when provided with a dataset of question-answer pairs for a number of images during training. A number of methods have focused on solving this problem by using image based attention. This is done by focusing on a specific part of the image while answering the question. Humans also do so when solving this problem. However, the regions that the previous systems focus on are not correlated with the regions that humans focus on. The accuracy is limited due to this drawback. In this paper, we propose to solve this problem by using an exemplar based method. We obtain one or more supporting and opposing exemplars to obtain a differential attention region. This differential attention is closer to human attention than other image based attention methods. It also helps in obtaining improved accuracy when answering questions. The method is evaluated on challenging benchmark datasets. We perform better than other image based attention methods and are competitive with other state of the art methods that focus on both image and questions.
Code (1)
Tasks
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
Video Question Answering via Attribute-Augmented Attention Network Learning
Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering appr…
AttributeInformation RetrievalMultiple-choiceQuestion Answering+5Multi-Level Attention Networks for Visual Question Answering
Inspired by the recent success of text-based question answering, visual question answering (VQA) is proposed to automatically answer natural language questions with the reference to a given image. Compared with text-base…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Hierarchical Question-Image Co-Attention for Visual Question Answering
A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in additi…
Visual DialogVisual Question AnsweringVisual Question Answering (VQA)Inverse Visual Question Answering with Multi-Level Attentions
In this paper, we propose a novel deep multi-level attention model to address inverse visual question answering. The proposed model generates regional visual and semantic features at the object level and then enhances th…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)On the Efficacy of Co-Attention Transformer Layers in Visual Question Answering
In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by a considerable margin. This improvement…
POSQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)