EaSe: A Diagnostic Tool for VQA Based on Answer DiversityShailza Jolly; Sandro Pezzelle; Moin Nabi
In: 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL-2021), June 6-11, Virtual, ACL, 2021.
We propose EASE, a simple diagnostic tool for Visual Question Answering (VQA) which quantifies the difficulty of an image, question sample. EASE is based on the pattern of answers provided by multiple annotators to a given question. In particular, it considers two aspects of the answers: (i) their Entropy; (ii) their Semantic content. First, we prove the validity of our diagnostic to identify samples that are easy/hard for state-of-art VQA models. Second, we show that EASE can be successfully used to select the most-informative samples for training/fine-tuning. Crucially, only information that is readily available in any VQA dataset is used to compute its scores.