Gold Seeker:面向目标的视觉和语言推理的策略分布信息增益
Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Langauge Reasoning
摘要:
随着计算机视觉从被动的像素分析转向主动的语义分析,需要进行推理的信息算法的广度已经显著扩展。在这种情况下,一个关键的挑战是能够识别所需的信息,作出决定,并选择一个行动,将恢复it.We提出了一个学习的方法,保持分布在其内部信息,从而明确表示的模糊性,它知道什么,需要知道,实现其目标。然后根据该分布生成潜在的动作。对于每个潜在的行动,计算预期结果的分布,并评估潜在信息增益的价值。所采取的行动是使潜在的信息增益最大化。我们证明了这种方法适用于两个视觉和语言的问题,吸引了显着的最近的兴趣,视觉对话和视觉查询生成。在这两种情况下,该方法积极选择最能减少其内部不确定性的行动,并在实现挑战目标方面优于竞争对手。
英文摘要:
As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will recover it. We propose a reinforcement-learning approach that maintains a distribution over its internal information, thus explicitly representing the ambiguity in what it knows, and needs to know, towards achieving its goal. Potential actions are then generated according to this distribution. For each potential action a distribution of the expected outcomes is calculated, and the value of the potential information gain assessed. The action taken is that which maximizes the potential information gain. We demonstrate this approach applied to two vision-and-language problems that have attracted significant recent interest, visual dialog and visual query generation. In both cases, the method actively selects actions that will best reduce its internal uncertainty and outperforms its competitors in achieving the goal of the challenge.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。