Efficient deep-narrow residual networks using dilated pooling for scene recognition

作者：Qiao, Zhinan; Yuan, Xiaohui^*; Zhang, Runmei; Chen, Tian; Zhang, Chaoning

来源：EXPERT SYSTEMS WITH APPLICATIONS, 2023, 234: 121018.

DOI：10.1016/j.eswa.2023.121018

• Convolutional Neural Network
• Scene recognition
• Efficient learning

This paper aims to address the challenges posed by complex scenery image classification. Most of the existing deep learning networks are trained and evaluated using ImageNet. However, when these models are applied to scenery images, dramatic performance degradation is observed due to the change in data characteristics. To challenge the prevailing practices in network design, we investigate the impact of altering data on the performance of deep networks. Specifically, we introduce a novel data-oriented network design to emphasize the importance of considering the unique characteristics of the data. Our proposed approach is a Deep-Narrow Network, which incorporates a Dilated Pooling module built upon the ResNet architecture. Compared to ResNet, our approach achieves a significant reduction of floating-point operations by 51.5% and in the number of parameters by 54.5%. Remarkably, despite the reduction in computational complexity and model size, our design exhibits a 0.4% increase in overall accuracy. This approach offers an efficient and effective means of scaling the network according to the data characteristics while maintaining highly competitive performance.