Tutorial on Answering Questions about Images with Deep Learning
This is an incremental tutorial for researchers and practitioners in computer vision and NLP, focusing on building architectures for visual question answering.
The paper tackles the problem of answering questions about images using deep learning, presenting a neural-based approach that achieves competitive performance on DAQUAR and VQA datasets, with models among the best using LSTM and global CNN representations.
Together with the development of more accurate methods in Computer Vision and Natural Language Understanding, holistic architectures that answer on questions about the content of real-world images have emerged. In this tutorial, we build a neural-based approach to answer questions about images. We base our tutorial on two datasets: (mostly on) DAQUAR, and (a bit on) VQA. With small tweaks the models that we present here can achieve a competitive performance on both datasets, in fact, they are among the best methods that use a combination of LSTM with a global, full frame CNN representation of an image. We hope that after reading this tutorial, the reader will be able to use Deep Learning frameworks, such as Keras and introduced Kraino, to build various architectures that will lead to a further performance improvement on this challenging task.