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 2302.04815cs.CVeess.IV
收藏

感知还是不感知:轻量级堆叠沙漏网络

To Perceive or Not to Perceive: Lightweight Stacked Hourglass Network

MBZUAI(穆罕默德·本·扎耶德人工智能大学)

Jameel Hassan Abdul Samadh, Salwa K. Al Khatib

摘要:

人体姿态估计(HPE)是计算机视觉中的经典任务,其关注于通过识别人的关节的位置来表示人的取向。我们设计了一个轻量级的堆叠沙漏网络模型的性能损失最小。轻量的2堆叠沙漏具有减少数量的通道,其具有可分离的回旋、具有级联的剩余连接以及沙漏的颈部之间的剩余连接。最终模型的性能略有下降,参数数量减少了79%,MAds也有类似的下降

英文摘要:

Human pose estimation (HPE) is a classical task in computer vision that focuses on representing the orientation of a person by identifying the positions of their joints. We design a lighterversion of the stacked hourglass network with minimal loss in performance of the model. The lightweight 2-stacked hourglass has a reduced number of channels with depthwise separable convolutions, residual connections with concatenation, and residual connections between the necks of the hourglasses. The final model has a marginal drop in performance with 79% reduction in the number of parameters and a similar drop in MAdds

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。

↑