2018 · 102 citations · 36 references
ComputingComputer ScienceComputer VisionMachine LearningVisual AttentionExplainable Machine LearningExplanationMultimodal InteractionNatural Language UnderstandingQuestion AnsweringVisual Question AnsweringActivity RecognitionAttentionBenchmark DatasetsExplainable Visual Question AnsweringMultimodal ExplanationRationale GenerationTextual ExplanationsVisual Explanations
Deep models that are both effective and explainable are desirable in many settings; prior explainable models have been unimodal, offering either image-based visualization of attention weights or text-based generation of post-hoc justifications. We propose a multimodal approach to explanation, and argue that the two modalities provide complementary explanatory strengths. We collect two new datasets to define and evaluate this task, and propose a novel model which can provide joint textual rationale generation and attention visualization. Our datasets define visual and textual justifications of a classification decision for activity recognition tasks (ACT-X) and for visual question answering tasks (VQA-X). We quantitatively show that training with the textual explanations not only yields better textual justification models, but also better localizes the evidence that supports the decision. We also qualitatively show cases where visual explanation is more insightful than textual explanation, and vice versa, supporting our thesis that multimodal explanation models offer significant benefits over unimodal approaches.
36
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
ROUGE: A Package for Automatic Evaluation of Summaries
Chin-Yew Lin · 2004 · 8.3K citations
VQA: Visual Question Answering
Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu et al. · 2015 · 4.3K citations