通过对抗训练克服遥感视觉问答中的语言偏见
Overcoming Language Bias in Remote Sensing Visual Question Answering via Adversarial Training
AI总结：
针对遥感视觉问答中的语言偏见问题，提出带对抗分支和两种正则化约束的VQA框架，并设计结合准确率与随机图像性能下降的评价指标，实验验证了方法有效性。
摘要：
视觉问答（VQA）系统提供了友好的用户界面，并使人机交互成为可能。然而，VQA模型普遍面临语言偏见的挑战，这种偏见源于所学习到的问题与答案之间的表层相关性。为解决这一问题，本研究提出了一种新颖框架，用于降低遥感数据VQA（RSVQA）的语言偏见。具体而言，我们在原始VQA框架中加入一个对抗分支。基于该对抗分支，我们引入两个正则化项来约束训练过程，以抵抗语言偏见。此外，为评估语言偏见方面的性能，我们提出了一种新指标，将标准准确率与引入问题和随机图像信息时的性能下降相结合。实验结果证明了本方法的有效性。我们相信，本方法能够为未来在RSVQA任务上减少语言偏见的工作提供启发。
英文摘要：
The Visual Question Answering (VQA) system offers a user-friendly interface and enables human-computer interaction. However, VQA models commonly face the challenge of language bias, resulting from the learned superficial correlation between questions and answers. To address this issue, in this study, we present a novel framework to reduce the language bias of the VQA for remote sensing data (RSVQA). Specifically, we add an adversarial branch to the original VQA framework. Based on the adversarial branch, we introduce two regularizers to constrain the training process against language bias. Furthermore, to evaluate the performance in terms of language bias, we propose a new metric that combines standard accuracy with the performance drop when incorporating question and random image information. Experimental results demonstrate the effectiveness of our method. We believe that our method can shed light on future work for reducing language bias on the RSVQA task.
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。
