Probabilistic framework for solving visual dialog

PATTERN RECOGNITION

卷:110

Article

Patro, Badri N.¹  Anupriy²  Namboodiri, Vinay P.² 

[1] Indian Inst Technol Kanpur, Dept Elect Engn, Kanpur, Uttar Pradesh, India

[2] Indian Inst Technol Kanpur, Dept Comp Sci & Engn, Kanpur, Uttar Pradesh, India

关键词: CNN;    LSTM;    Uncertainty;    Aleatoric uncertainty;    Epistemic uncertainty vision and language;    Visual dialog;    VQA;    Answer generation;    Question generation;    Bayesian deep learning;   

DOI  :  10.1016/j.patcog.2020.107586

来源: Elsevier

【 摘 要 】

In this paper, we propose a probabilistic framework for solving the task of 'Visual Dialog'. Solving this task requires reasoning and understanding of visual modality, language modality, and common sense knowledge to answer. Various architectures have been proposed to solve this task by variants of multi -modal deep learning techniques that combine visual and language representations. However, we believe that it is crucial to understand and analyze the sources of uncertainty for solving this task. Our approach allows for estimating uncertainty and also aids a diverse generation of answers. The proposed approach is obtained through a probabilistic representation module that provides us with representations for image, question and conversation history, a module that ensures that diverse latent representations for candidate answers are obtained given the probabilistic representations and an uncertainty representation module that chooses the appropriate answer that minimizes uncertainty. We thoroughly evaluate the model with a detailed ablation analysis, comparison with state of the art and visualization of the uncertainty that aids in the understanding of the method. Using the proposed probabilistic framework, we thus obtain an improved visual dialog system that is also more explainable. (c) 2020 Elsevier Ltd. All rights reserved.

【 授权许可】

Free