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 2301.04608cs.CVcs.LG
收藏

填充模块:学习深度神经网络中的填充

Padding Module: Learning the Padding in Deep Neural Networks

University of Nebraska Omaha(内布拉斯加大学奥马哈分校)

Fahad Alrasheedi, Xin Zhong, Pei-Chi Huang

摘要:

在过去的几十年中,许多研究致力于提高神经网络的性能,例如网络结构,初始化和激活。然而,研究可学习填充方法在深度学习中的重要性和效果仍然相对开放。为了弥补这一差距,本文提出了一种新的可训练填充模块,可以放置在深度学习模型中。Padding Module可以在不需要或影响模型的整个损失函数的情况下优化自身。为了训练自身,填充模块通过利用用于监督的输入数据中的底层结构来从输入构建地面实况和预测器。因此,填充模块可以自动学习将像素填充到其输入图像或特征图的边界。填充内容是对其输入数据的实际扩展,同时促进了深度学习模型的下游任务。实验表明,所提出的填充模块优于国家的最先进的竞争对手和基线方法。例如,在VGG16和ResNet50上测试时,Padding模块的分类精度比零填充高1.23%和0.44%。

英文摘要:

During the last decades, many studies have been dedicated to improving the performance of neural networks, for example, the network architectures, initialization, and activation. However, investigating the importance and effects of learnable padding methods in deep learning remains relatively open. To mitigate the gap, this paper proposes a novel trainable Padding Module that can be placed in a deep learning model. The Padding Module can optimize itself without requiring or influencing the model's entire loss function. To train itself, the Padding Module constructs a ground truth and a predictor from the inputs by leveraging the underlying structure in the input data for supervision. As a result, the Padding Module can learn automatically to pad pixels to the border of its input images or feature maps. The padding contents are realistic extensions to its input data and simultaneously facilitate the deep learning model's downstream task. Experiments have shown that the proposed Padding Module outperforms the state-of-the-art competitors and the baseline methods. For example, the Padding Module has 1.23% and 0.44% more classification accuracy than the zero padding when tested on the VGG16 and ResNet50.

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。

↑