FPANet: Feature-enhanced position attention network for semantic segmentation

Xu, Haixia; Wang, Shuailong; Huang, Yunjia; Zhou, Wei; Chen, Qilai; Zhang, Dongbo

doi:10.1007/s00138-021-01246-x

Cited by 7 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al 45 first proposed to apply the self-attention module to the GAN and also discussed which layer of the network the attention mechanism is placed in to help obtain better results. FPANet 46 designed a feature integration module to form a feature-enhanced location attention module, which enhances the discrimination of features. Chen et al 47 proposed a self-attention mechanism for single-image generation against networks, and discussed the changes of the model when the self-attention mechanism is placed in different positions of the generator.…”

Section: Self-attention Mechanismmentioning

confidence: 99%

See 1 more Smart Citation

Image restoration fabric defect detection based on the dual generative adversarial network patch model

Liang

Líu

2022

Textile Research Journal

View full text Add to dashboard Cite

The training of supervised learning requires the use of ground truth, which is difficult to obtain in large quantities in production practice. Unsupervised learning requires only flawless and anomalous images of fabrics, but inevitably generates a great deal of background noise when performing result generation, which reduces the quality of results. To overcome these limitations, we propose a new approach: image restoration fabric defect detection based on the dual generative adversarial network patch model (DGPM). We train with a modified generative adversarial network using only flawless and anomalous images of the fabric. We propose the patch model to directly obtain specific information about fabric defects and add a self-attentive model to reduce the generation of background noise. The performance of the DGPM is evaluated on box-, star-, and dot-patterned fabric databases. The true positive rate (TPR) of the box type is 81.56% and the f-measure is 62.69%, the TPR of the dot type is 83.72% and the f-measure is 67.33%, and the TPR of the star type is 79.79% and the f-measure is 64.65%.

show abstract

Section: Self-attention Mechanismmentioning

confidence: 99%

“…45 first proposed to apply the self-attention module to the GAN and also discussed which layer of the network the attention mechanism is placed in to help obtain better results. FPANet 46 designed a feature integration module to form a feature-enhanced location attention module, which enhances the discrimination of features. Chen et al.…”

Section: Related Workmentioning

confidence: 99%