A closer look at network resolution for efficient network design

by   Taojiannan Yang, et al.
UNC Charlotte
Michigan State University

There is growing interest in designing lightweight neural networks for mobile and embedded vision applications. Previous works typically reduce computations from the structure level. For example, group convolution based methods reduce computations by factorizing a vanilla convolution into depth-wise and point-wise convolutions. Pruning based methods prune redundant connections in the network structure. In this paper, we explore the importance of network input for achieving optimal accuracy-efficiency trade-off. Reducing input scale is a simple yet effective way to reduce computational cost. It does not require careful network module design, specific hardware optimization and network retraining after pruning. Moreover, different input scales contain different representations to learn. We propose a framework to mutually learn from different input resolutions and network widths. With the shared knowledge, our framework is able to find better width-resolution balance and capture multi-scale representations. It achieves consistently better ImageNet top-1 accuracy over US-Net under different computation constraints, and outperforms the best compound scale model of EfficientNet by 1.5 framework is also validated on COCO object detection and instance segmentation as well as transfer learning.


Accelerate Your CNN from Three Dimensions: A Comprehensive Pruning Framework

To deploy a pre-trained deep CNN on resource-constrained mobile devices,...

Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution

This paper proposes a novel module called middle spectrum grouped convol...

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

High-resolution images enable neural networks to learn richer visual rep...

Rethinking the Detection Head Configuration for Traffic Object Detection

Multi-scale detection plays an important role in object detection models...

CSL-YOLO: A New Lightweight Object Detection System for Edge Computing

The development of lightweight object detectors is essential due to the ...

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

In natural images, information is conveyed at different frequencies wher...

Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff

Existing salient object detection methods often adopt deeper and wider n...

Please sign up or login with your details

Forgot password? Click here to reset