Look ATME: The Discriminator Mean Entropy Needs Attention

Solano-Carrillo, E.; Rodriguez, Angel Bueno; Carrillo-Perez, Borja; Steiniger, Yannik; Stoppe, Jannis

doi:10.1109/cvprw59228.2023.00086

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Song et al 31 proposed Semi-MapGen and designed extension loss and channel loss to improve the accuracy of map generation through knowledge extension learning strategies. Solano-Carrillo et al 32 proposed the fully supervised model ATME, which enhanced the connection between the generator and the discriminator by focusing on the average entropy of the discriminator. They efficiently generated maps by integrating the high-quality generation ability of DMs and the sampling strength of GANs.…”

Section: Map Generation Methods Based On Generative Adversarial Networkmentioning

confidence: 99%

See 1 more Smart Citation

Improved SmapGAN remote sensing image map generation based on multi-head self-attention and carafe

Ding,

Wang,

Sun

et al. 2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

The changes in ground roads, buildings, and occurrences of natural disasters lead to mismatches between the actual ground conditions and existing maps. Through style transfer between real-time remote sensing images and maps, map content can be rapidly generated and updated. However, in existing methods for generating maps from remote sensing images based on SmapGAN, we first found that using ResBlock as the style conversion module fails to establish long-distance relationships between features. In addition, the small receptive field of convolution layers in ResBlock leads to poor global information capture, resulting in inferior image restoration during upsampling. Second, using transpose convolution as the upsampling method can result in the issue of blurred content in the generated maps. To address these problems, we propose corresponding improvements: on one hand, a style conversion module combining multi-headed self-attention (MHSA) with residual modules, named MHSA-ResBlock, is introduced to address the difficulty in capturing long-distance relationships between features when dealing with a large number of pixel features, and to better capture global information in images. On the other hand, an upsampling method combining transpose convolution with the CARAFE upsampling operator, named TC-Carafe, is proposed to tackle the issues of content loss and blurring associated with traditional transpose convolution upsampling. Furthermore, experimental results show that the MHSA-ResBlock establishes inter-pixel feature relationships and leverages the advantages of fine-grained upsampling operations with TC-Carafe, thereby utilizing inter-pixel feature relationships and neighborhood information to further improve the quality of map generation. Compared to SmapGAN, our research method has shown improvements of 0.6133 and 0.0042 in PSNR and SSIM, respectively. In addition, it has reduced RMSE by 0.72, outperforming SmapGAN in all metrics.

show abstract

Section: Map Generation Methods Based On Generative Adversarial Networkmentioning

confidence: 99%

“…The experiment selected SmapGAN, 10 CycleGAN, 8 Pix2pixHD, 7 CUT_MoNCE, 30 and ATME 32 comparing with the method, and use the PSNR, SSIM and RMSE evaluation metric for testing and evaluation.…”

Section: Performance and Comparisonmentioning

confidence: 99%

Improved SmapGAN remote sensing image map generation based on multi-head self-attention and carafe

Ding,

Wang,

Sun

et al. 2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

An improved infrared simulation method based on generative adversarial networks

Lyu,

Jia,

Liu

et al. 2024

Infrared Physics & Technology

View full text Add to dashboard Cite

SIDGAN: Efficient Multi-Module Architecture for Single Image Defocus Deblurring

Ling,

Zhan,

Cao

2024

Electronics

View full text Add to dashboard Cite

In recent years, with the rapid developments in deep learning and graphics processing units, learning-based defocus deblurring has made favorable achievements. However, the current methods are not effective in processing blurred images with a large depth of field. The greater the depth of field, the blurrier the image, namely, the image contains large blurry regions and encounters severe blur. The fundamental reason for the unsatisfactory results is that it is difficult to extract effective features from the blurred images with large blurry regions. For this reason, a new FFEM (Fuzzy Feature Extraction Module) is proposed to enhance the encoder’s ability to extract features from images with large blurry regions. After using the FFEM during encoding, its PSNR (Peak Signal-to-Noise Ratio) is improved by 1.33% on the DPDD (Dual-Pixel Defocus Deblurring). Moreover, images with large blurry regions often cause the current algorithms to generate artifacts in their results. Therefore, a new module named ARM (Artifact Removal Module) is proposed in this work and employed during decoding. After utilizing the ARM during decoding, its PSNR is improved by 2.49% on the DPDD. After using the FFEM and the ARM simultaneously, compared to the latest algorithms, the PSNR of our method is improved by 3.29% on the DPDD. Following the previous research in this field, qualitative and quantitative experiments are conducted on the DPDD and the RealDOF (Real Depth of Field), and the experimental results indicate that our method surpasses the state-of-the-art algorithms in three objective metrics.

show abstract

Look ATME: The Discriminator Mean Entropy Needs Attention

Cited by 3 publications

References 15 publications

Improved SmapGAN remote sensing image map generation based on multi-head self-attention and carafe

Improved SmapGAN remote sensing image map generation based on multi-head self-attention and carafe

An improved infrared simulation method based on generative adversarial networks

SIDGAN: Efficient Multi-Module Architecture for Single Image Defocus Deblurring

Contact Info

Product

Resources

About