论文标题
深度等距学习以视觉识别
Deep Isometric Learning for Visual Recognition
论文作者
论文摘要
据信初始化，归一化和跳过连接是训练非常深的卷积神经网络并获得最新性能的三种必不可少的技术。本文表明，在没有标准化的情况下，深度的香草弯曲也可以训练，以在标准图像识别基准上取得出色的良好性能。这是通过在初始化和训练期间实施卷积内核以及使用偏移变体的变体，从而实现的。进一步的实验表明，如果与跳过连接相结合，那么近等轴测网络也可以与（对于ImageNet）达到（可可）的（对于可可）标准重新NET，即使完全没有归一化。我们的代码可在https://github.com/haozhiqi/isonet上找到。
Initialization, normalization, and skip connections are believed to be three indispensable techniques for training very deep convolutional neural networks and obtaining state-of-the-art performance. This paper shows that deep vanilla ConvNets without normalization nor skip connections can also be trained to achieve surprisingly good performance on standard image recognition benchmarks. This is achieved by enforcing the convolution kernels to be near isometric during initialization and training, as well as by using a variant of ReLU that is shifted towards being isometric. Further experiments show that if combined with skip connections, such near isometric networks can achieve performances on par with (for ImageNet) and better than (for COCO) the standard ResNet, even without normalization at all. Our code is available at https://github.com/HaozhiQi/ISONet.
