Learning Features with Parameter-Free Layers
Preprint
Abstract
Trainable layers such as convolutional building blocks are the standard network design choices by learning parameters to capture the global context through successive spatial operations. When designing an efficient network, trainable layers such as the depthwise convolution is the source of efficiency in the number of parameters and FLOPs, but there was little improvement to the model speed in practice. This paper argues that simple built-in parameter-free operations can be a favorable alternative to the efficient trainable layers replacing spatial operations in a network architecture. We aim to break the stereotype of organizing the spatial operations of building blocks into trainable layers. Extensive experimental analyses based on layer-level studies with fully-trained models and neural architecture searches are provided to investigate whether parameter-free operations such as the max-pool are functional. The studies eventually give us a simple yet effective idea for redesigning network architectures, where the parameter-free operations are heavily used as the main building block without sacrificing the model accuracy as much. Experimental results on the ImageNet dataset demonstrate that the network architectures with parameter-free operations could enjoy the advantages of further efficiency in terms of model speed, the number of the parameters, and FLOPs. Code and ImageNet pretrained models are available at https://github.com/naver-ai/PfLayer.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search2020
- Optimizing Grouped Convolutions on Edge Devices2020
- Data-Driven Sparse Structure Selection for Deep Neural Networks2018
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Networks with Stochastic Depth2016
- Identity Mappings in Deep Residual Networks2016
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- Going deeper with convolutions2015
- Microsoft COCO: Common Objects in Context2014