Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
This work addresses the problem of inefficient visual question generation for AI systems, though it is incremental as it builds on existing datasets and methods.
The paper tackles the challenge of generating intelligent, goal-oriented questions about images by proposing a Deep Reinforcement Learning framework with intermediate rewards, resulting in questions that help identify objects in images at a much higher success rate on the GuessWhat?! dataset.
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of insane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard Guesser identify a specific object in an image at a much higher success rate.