Active Learning for Visual Question Answering: An Empirical Study
This work addresses the challenge of reducing annotation costs for VQA systems, but it is incremental as it builds on existing active learning methods with empirical validation.
The study tackled the problem of improving Visual Question Answering models under limited query budgets by empirically comparing active learning approaches, finding that once models have sufficient data, all methods outperform random selection with significant query savings, and a proposed goal-driven scoring function performed best in specific evaluation scenarios.
We present an empirical study of active learning for Visual Question Answering, where a deep VQA model selects informative question-image pairs from a pool and queries an oracle for answers to maximally improve its performance under a limited query budget. Drawing analogies from human learning, we explore cramming (entropy), curiosity-driven (expected model change), and goal-driven (expected error reduction) active learning approaches, and propose a fast and effective goal-driven active learning scoring function to pick question-image pairs for deep VQA models under the Bayesian Neural Network framework. We find that deep VQA models need large amounts of training data before they can start asking informative questions. But once they do, all three approaches outperform the random selection baseline and achieve significant query savings. For the scenario where the model is allowed to ask generic questions about images but is evaluated only on specific questions (e.g., questions whose answer is either yes or no), our proposed goal-driven scoring function performs the best.