arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.06457cs.CV
收藏

基于注意力图熵的主动视觉探索

Active Visual Exploration Based on Attention-Map Entropy

IDEAS NCBR;Jagiellonian University(雅盖隆大学);Warsaw University of Technology(华沙理工大学);Tooploox;Ardigen

Adam Pardyl, Grzegorz Rypeść, Grzegorz Kurzejamski, Bartosz Zieliński, Tomasz Trzciński

AI总结:

本文提出注意力图熵(AME)方法,利用Transformer内部不确定性选择最具信息量的观测,无需额外损失即可简化训练,并在模拟视网膜传感器的实验中显著提升重建、分割和分类性能。

摘要:

主动视觉探索旨在解决现实场景中传感器能力受限的问题,其中后续观测是基于环境主动选择的。为了解决这一问题,我们提出了一种新技术,称为注意力图熵(Attention-Map Entropy,AME)。它利用基于Transformer模型内部的预测不确定性来确定最具信息量的观测。与现有方案相比,该方法不需要额外的损失分量,从而简化了训练过程。通过模拟视网膜式传感器的实验,我们表明这种简化的训练显著提升了在公开数据集上的重建、分割和分类性能。

英文摘要:

Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment. To tackle this problem, we introduce a new technique called Attention-Map Entropy (AME). It leverages the internal uncertainty of the transformer-based model to determine the most informative observations. In contrast to existing solutions, it does not require additional loss components, which simplifies the training. Through experiments, which also mimic retina-like sensors, we show that such simplified training significantly improves the performance of reconstruction, segmentation and classification on publicly available datasets.

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。

↑