ABSTRACT
Deep convolutional neural networks are powerful and popular tools as deep learning emerges in recent years for image classification in computer vision. However, it is difficult to learn convolutional filters from the examples. The innate frequency property of the data has not been well considered. To address this problem, we find high-frequency information import within deep networks and therefore propose our high-pass attention method (HPA) to help the learning process. HPA explicitly generates high-frequency information via a stage-wise high-pass filter to alleviate the burden of learning such information. Strengthened by channel attention on the concatenated features, our method demonstrates consistent improvements upon ResNet-18/ResNet-50 by 1.36%/1.60% and 1.47%/1.39% on the ImageNet-1K dataset and the Food-101 dataset, respectively, as well as the effectiveness over a variety of modules.
- Yunpeng Chen, Haoqi Fan, Bing Xu, Zhicheng Yan, Yannis Kalantidis, Marcus Rohrbach, Shuicheng Yan, and Jiashi Feng. 2019. Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution. In Proceedings of CVPR. 3435–3444.Google ScholarCross Ref
- Bowen Cheng, Rong Xiao, Jianfeng Wang, Thomas Huang, and Lei Zhang. 2020. High frequency residual learning for multi-scale image classification. In 30th British Machine Vision Conference, BMVC 2019.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision. 1026–1034.Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of CVPR. 770–778.Google ScholarCross Ref
- Geoffrey E Hinton, Alex Krizhevsky, and Ilya Sutskever. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012), 1106–1114.Google Scholar
- Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-excitation networks. In Proceedings of CVPR. 7132–7141.Google ScholarCross Ref
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of Machine Learning Research, Vol. 37. 448–456.Google Scholar
- Qiufu Li, Linlin Shen, Sheng Guo, and Zhihui Lai. 2020. Wavelet integrated cnns for noise-robust image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7245–7254.Google ScholarCross Ref
- Pengju Liu, Hongzhi Zhang, Wei Lian, and Wangmeng Zuo. 2019. Multi-level wavelet convolutional neural networks. IEEE Access 7 (2019), 74973–74985.Google ScholarCross Ref
- Jongchan Park, Sanghyun Woo, Joon-Young Lee, and In-So Kweon. 2018. BAM: Bottleneck Attention Module. In British Machine Vision Conference (BMVC). British Machine Vision Association (BMVA).Google Scholar
- Zhinan Qiao, Xiaohui Yuan, and Mohamed Elhoseny. 2020. Urban Scene Recognition via Deep Network Integration. In Urban Intelligence and Applications. Singapore, 135–149.Google Scholar
- Haohan Wang, Xindi Wu, Zeyi Huang, and Eric P Xing. 2020. High-frequency Component Helps Explain the Generalization of Convolutional Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8684–8694.Google ScholarCross Ref
- Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. Cbam: Convolutional block attention module. In Proceedings of ECCV. 3–19.Google ScholarDigital Library
- Xiaohui Yuan, Zhinan Qiao, and Abolfazl Meyarian. 2022. Scale Attentive Network for Scene Recognition. Neurocomputing 492 (2022), 612–623.Google ScholarDigital Library
- Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In Proceedings of ECCV. 818–833.Google ScholarCross Ref
- Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations.Google Scholar
- Richard Zhang. 2019. Making Convolutional Networks Shift-Invariant Again. In International Conference on Machine Learning. 7324–7334.Google Scholar
Index Terms
- Improved Convolutional Neural Networks by Integrating High-frequency Information for Image Classification
Recommendations
Convergence of deep convolutional neural networks
AbstractConvergence of deep neural networks as the depth of the networks tends to infinity is fundamental in building the mathematical foundation for deep learning. In a previous study, we investigated this question for deep networks with the Rectified ...
Efficient densely connected convolutional neural networks
Highlights- Proposed two efficient densely connected ConvNets, DesneDsc and Dense2Net.
- ...
Graphical abstractDisplay Omitted
AbstractRecent works have shown that convolutional neural networks (CNNs) are parameter redundant, which limits the application of CNNs in Mobile devices with limited memory and computational resources. In this paper, two novel and efficient ...
Learning to trade in financial time series using high-frequency through wavelet transformation and deep reinforcement learning
AbstractDeep learning-based financial approaches have received attention from both investors and researchers. This study demonstrates how to optimize portfolios, asset allocation, and trading systems based on deep reinforcement learning using three ...
Comments