arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.09398cs.CV
收藏

Learnable Histogram:深度神经网络的统计上下文特征

Learnable Histogram: Statistical Context Features for Deep Neural Networks

The Chinese University of Hong Kong(香港中文大学)

Zhe Wang, Hongsheng Li, Wanli Ouyang, Xiaogang Wang

摘要:

统计特征,如直方图,词袋(BoW)和Fisher向量,通常与传统分类方法中的手工特征一起使用,但由于深度学习方法的流行,引起的关注较少。在本文中,我们提出了一个可学习的直方图层,它在端到端训练中学习深度神经网络中的直方图特征。这样的层能够反向传播(BP)错误,学习最佳的bin中心和bin宽度,并在训练期间与深度网络中的其他层联合优化。通过将可学习直方图层集成到深度网络中,探索了两个视觉问题,即语义分割和目标检测,这表明所提出的层可以很好地推广到不同的应用。进行深入调查,以提供对新引入的层的见解。

英文摘要:

Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods. In this paper, we propose a learnable histogram layer, which learns histogram features within deep neural networks in end-to-end training. Such a layer is able to back-propagate (BP) errors, learn optimal bin centers and bin widths, and be jointly optimized with other layers in deep networks during training. Two vision problems, semantic segmentation and object detection, are explored by integrating the learnable histogram layer into deep networks, which show that the proposed layer could be well generalized to different applications. In-depth investigations are conducted to provide insights on the newly introduced layer.

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。

↑