Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
arXiv:1905.03672
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.
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Neural Architecture Search: A Survey
- Xception: Deep Learning with Depthwise Separable Convolutions
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- Rethinking ImageNet Pre-training
- Interleaved Group Convolutions for Deep Neural Networks
- IGCV: Interleaved Structured Sparse Convolutional Neural Networks