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 1706.02735cs.CV
收藏

CortexNet:一个鲁棒的可视时间表示的通用网络族

CortexNet: a Generic Network Family for Robust Visual Temporal Representations

Purdue University(普渡大学)

Alfredo Canziani, Eugenio Culurciello

摘要:

在过去的五年里,我们已经观察到,在监督下训练的前馈神经网络在视觉相关任务中表现非常出色。这些模型在静态图像中的对象识别、定位和检测方面实现了超人的性能。然而,有必要确定最佳策略,采用这些网络与时间视觉输入,并获得一个强大的和稳定的视频数据表示。受人类视觉系统的启发,我们提出了一个深度神经网络家族,CortexNet,它不仅具有自下而上的前馈连接,而且还模拟了我们视觉皮层中存在的丰富的自上而下的反馈和横向连接。我们介绍了两种训练方案-无监督的MatchNet和弱监督的TempoNet模式-其中网络通过学习自我运动线索以及如何自动跟踪当前场景中的多个对象来学习如何正确预测视频剪辑中的后续帧或其主要主体的身份。在https://engineering.purdue.edu/elab/CortexNet/上找到该项目的网站。

英文摘要:

In the past five years we have observed the rise of incredibly well performing feed-forward neural networks trained supervisedly for vision related tasks. These models have achieved super-human performance on object recognition, localisation, and detection in still images. However, there is a need to identify the best strategy to employ these networks with temporal visual inputs and obtain a robust and stable representation of video data. Inspired by the human visual system, we propose a deep neural network family, CortexNet, which features not only bottom-up feed-forward connections, but also it models the abundant top-down feedback and lateral connections, which are present in our visual cortex. We introduce two training schemes - the unsupervised MatchNet and weakly supervised TempoNet modes - where a network learns how to correctly anticipate a subsequent frame in a video clip or the identity of its predominant subject, by learning egomotion clues and how to automatically track several objects in the current scene. Find the project website at https://engineering.purdue.edu/elab/CortexNet/.

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。

↑