A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning

Yu, Yankun; Huan, Liu; Fu, Minghan; Chen, Jun; Wang, Xiyao; Wang, Keyan

doi:10.48550/arxiv.2104.08902

Cited by 1 publication

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, pre-trained models can reduce the overfitting problem caused by the limited wound images [41]. We employ pre-trained ResNet and Res2Net, discarding fully connected layers [42]. As shown in Figure 1a, we introduce the feature attention module after the Res2Net convolutional layer in HF-Net, which consists of multiple local residual connections and the feature attention [43].…”

Section: Hf-netmentioning

confidence: 99%

Multi-Class Wound Classification via High and Low-Frequency Guidance Network

Guo,

Yi,

Dong

et al. 2023

Bioengineering

View full text Add to dashboard Cite

Wound image classification is a crucial preprocessing step to many intelligent medical systems, e.g., online diagnosis and smart medical. Recently, Convolutional Neural Network (CNN) has been widely applied to the classification of wound images and obtained promising performance to some extent. Unfortunately, it is still challenging to classify multiple wound types due to the complexity and variety of wound images. Existing CNNs usually extract high- and low-frequency features at the same convolutional layer, which inevitably causes information loss and further affects the accuracy of classification. To this end, we propose a novel High and Low-frequency Guidance Network (HLG-Net) for multi-class wound classification. To be specific, HLG-Net contains two branches: High-Frequency Network (HF-Net) and Low-Frequency Network (LF-Net). We employ pre-trained models ResNet and Res2Net as the feature backbone of the HF-Net, which makes the network capture the high-frequency details and texture information of wound images. To extract much low-frequency information, we utilize a Multi-Stream Dilation Convolution Residual Block (MSDCRB) as the backbone of the LF-Net. Moreover, a fusion module is proposed to fully explore informative features at the end of these two separate feature extraction branches, and obtain the final classification result. Extensive experiments demonstrate that HLG-Net can achieve maximum accuracy of 98.00%, 92.11%, and 82.61% in two-class, three-class, and four-class wound image classifications, respectively, which outperforms the previous state-of-the-art methods.

show abstract

Section: Hf-netmentioning

confidence: 99%