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 2201.12047cs.CV
收藏

探索用于RGB-D SLAM的物体感知注意力引导帧关联方法

Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM

Ali Caglayan, Nevrez Imamoglu, Oguzhan Guclu, Ali Osman Serhatoglu, Weimin Wang, Ahmet Burak Can, Ryosuke Nakamura

AI总结:

本研究针对RGB-D室内SLAM任务,提出将逐层物体注意力信息与CNN层表征融合的方法,有效提升了帧关联性能,为SLAM等视觉任务的性能优化提供了新的思路。

摘要:

深度学习模型作为一个新兴研究方向,已在诸多领域取得显著进展。尤其是类激活映射方法等可视化工具,为卷积神经网络(CNNs)的推理过程提供了视觉层面的解释。通过利用网络层的梯度,能够展示网络在执行特定图像识别任务时的注意力聚焦区域。此外,这些梯度可与CNN特征相结合,用于定位场景中更具通用性的、依赖任务的注意力(显著)物体。尽管已有上述进展,但目前这类梯度(网络注意力)信息尚未被大量明确用于与CNN表征融合以提取物体语义。这一融合对同时定位与地图构建(SLAM)等视觉任务极具价值,因为空间注意力物体位置的CNN表征有望提升任务性能。因此,本研究提出将任务特定的网络注意力应用于RGB-D室内SLAM。为此,我们将逐层物体注意力信息(层梯度)与CNN层表征相融合,以提升一种RGB-D室内SLAM方法的帧关联性能。实验结果显示,该方法性能优于基线,效果可观。

英文摘要:

Deep learning models as an emerging topic have shown great progress in various fields. Especially, visualization tools such as class activation mapping methods provided visual explanation on the reasoning of convolutional neural networks (CNNs). By using the gradients of the network layers, it is possible to demonstrate where the networks pay attention during a specific image recognition task. Moreover, these gradients can be integrated with CNN features for localizing more generalized task dependent attentive (salient) objects in scenes. Despite this progress, there is not much explicit usage of this gradient (network attention) information to integrate with CNN representations for object semantics. This can be very useful for visual tasks such as simultaneous localization and mapping (SLAM) where CNN representations of spatially attentive object locations may lead to improved performance. Therefore, in this work, we propose the use of task specific network attention for RGB-D indoor SLAM. To do so, we integrate layer-wise object attention information (layer gradients) with CNN layer representations to improve frame association performance in an RGB-D indoor SLAM method. Experiments show promising results with improved performance over the baseline.

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。

↑