WSNet: Learning Compact and Efficient Networks with Weight Sampling

Xiaojie Jin, Yingzhen Yang, Ning Xu, Jianchao Yang, Jiashi Feng, Shuicheng Yan

Abstract: We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via \emph{ad hoc} processing such as model pruning or filter factorization. Alternatively, WSNet proposes learning model parameters by sampling from a compact set of learnable parameters, which naturally enforces {parameter sharing} throughout the learning process. We demonstrate that such a novel weight sampling approach (and induced WSNet) promotes both weights and computation sharing favorably. By employing this method, we can more efficiently learn much smaller networks with competitive performance compared to baseline networks with equal numbers of convolution filters. Specifically, we consider learning compact and efficient 1D convolutional neural networks for audio classification. Extensive experiments on multiple audio classification datasets verify the effectiveness of WSNet. Combined with weight quantization, the resulted models are up to \textbf{180$\times$} smaller and theoretically up to \textbf{16$\times$} faster than the well-established baselines, without noticeable performance drop.

TL;DR: We present a novel network architecture for learning compact and efficient deep neural networks

Keywords: Deep learning, model compression

Data: [2017 Robotic Instrument Segmentation Challenge](https://paperswithcode.com/dataset/2017-robotic-instrument-segmentation), [ESC-50](https://paperswithcode.com/dataset/esc-50), [UrbanSound8K](https://paperswithcode.com/dataset/urbansound8k-1)