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 2211.17045cs.CVcs.AI
收藏

从动作到事件:一种基于改进深度信念网络的迁移学习方法

From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks

São Paulo State University(圣保罗州立大学);Universidade Federal de São Paulo(圣保罗联邦大学)

Mateus Roder, Jurandy Almeida, Gustavo H. de Rosa, Leandro A. Passos, André L. D. Rossi, João P. Papa

摘要:

在过去的十年中,指数数据增长提供了基于机器学习的算法的能力,并使其能够在日常生活活动中使用。另外,这种改进部分地归因于深度学习技术的出现,即,一堆简单的架构,最终形成更复杂的模型。虽然这两个因素都产生了出色的结果,但它们也带来了学习过程的缺点,因为在大型数据集上训练复杂模型既昂贵又耗时。这样的问题在处理视频分析时更加明显。一些工作已经考虑了迁移学习或领域自适应,即,将知识从一个领域映射到另一个领域的方法,以减轻训练负担,但它们中的大多数都是在单个或小块帧上操作的。本文提出了一种新的方法来映射知识从动作识别到事件识别使用基于能量的模型,表示为光谱深度信念网络。这种模型可以同时处理所有帧,在学习过程中携带空间和时间信息。在两个公共视频数据集HMDB-51和UCF-101上进行的实验结果表明,与传统的基于能量的模型(如受限玻尔兹曼机和深度信念网络)相比,该模型的有效性及其减少的计算负担。

英文摘要:

In the last decade, exponential data growth supplied machine learning-based algorithms' capacity and enabled their usage in daily-life activities. Additionally, such an improvement is partially explained due to the advent of deep learning techniques, i.e., stacks of simple architectures that end up in more complex models. Although both factors produce outstanding results, they also pose drawbacks regarding the learning process as training complex models over large datasets are expensive and time-consuming. Such a problem is even more evident when dealing with video analysis. Some works have considered transfer learning or domain adaptation, i.e., approaches that map the knowledge from one domain to another, to ease the training burden, yet most of them operate over individual or small blocks of frames. This paper proposes a novel approach to map the knowledge from action recognition to event recognition using an energy-based model, denoted as Spectral Deep Belief Network. Such a model can process all frames simultaneously, carrying spatial and temporal information through the learning process. The experimental results conducted over two public video dataset, the HMDB-51 and the UCF-101, depict the effectiveness of the proposed model and its reduced computational burden when compared to traditional energy-based models, such as Restricted Boltzmann Machines and Deep Belief Networks.

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。

↑