Visual Question Generation as Dual Task of Visual Question Answering

Understand

Recently visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, which have been explored separately.

• In this work, we propose an end-to-end unified framework, the Invertible Question Answering Network (iQAN), to leverage the complementary relations between questions and answers in images by jointly training the model on VQA and VQG tasks.
• Corresponding parameter sharing scheme and regular terms are proposed as constraints to explicitly leverage Q,A's dependencies to guide the training process.
• After training, iQAN can take either question or answer as input, then output the counterpart.