Abstract
In this paper, we are interested in boosting the representation capability of convolution neural networks which utilizing the inverted residual structure. Based on the success of Inverted Residual structure[Sandler et al. 2018] and Interleaved Low-Rank Group Convolutions[Sun et al. 2018], we rethink this two pattern of neural network structure, rather than NAS(Neural architecture search) method[Zoph and Le 2017; Pham et al. 2018; Liu et al. 2018b], we introduce uneven point-wise group convolution, which provide a novel search space for designing basic blocks to obtain better trade-off between representation capability and computational cost. Meanwhile, we propose two novel information flow patterns that will enable cross-group information flow for multiple group convolution layers with and without any channel permute/shuffle operation. Dense experiments on image classification task show that our proposed model, named Seesaw-Net, achieves state-of-the-art(SOTA) performance with limited computation and memory cost. Our code will be open-source and available together with pre-trained models.
Abstract (translated)
本文旨在提高利用反向残差结构的卷积神经网络的表示能力。基于倒置残余结构的成功[Sandler等人2018]和交错低阶组卷积[Sun等人2018年),我们重新考虑了这两种神经网络结构模式,而不是nas(神经架构搜索)方法[Zoph和Le 2017;Pham等人2018年;Liu等人2018b]中,我们引入了不均匀点组卷积,这为设计基本块提供了一个新的搜索空间,以便在表示能力和计算成本之间获得更好的权衡。同时,我们提出了两种新的信息流模式,可以使多组卷积层在有或无任何信道排列/洗牌操作的情况下实现跨组信息流。对图像分类任务的密集实验表明,该模型名为seesaw-net,在有限的计算和存储成本下,达到了最先进的(sota)性能。我们的代码将是开放源码的,可与预先培训的模型一起使用。
URL
https://arxiv.org/abs/1905.03672