Self-Critical Reasoning for Robust Visual Question Answering
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 8601-8611, 2019.
Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different question-answer (QA) distribution . To address this issue, we introduce a self-critical training objective t...More
PPT (Upload PPT)