Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
This work addresses efficiency and performance trade-offs in neural network design for image classification, though it appears incremental by building on existing structures like inverted residuals and group convolutions.
The paper tackles the problem of boosting representation capability in convolutional neural networks with inverted residual structures by introducing uneven point-wise group convolution and novel information flow patterns, achieving state-of-the-art performance on image classification with limited computational and memory costs.
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.