Knowledge Distillation and Parameter Simplification for Power Operation and Maintenance-based LLMs DOI
Jing Fu,

Huaxi Wu,

Han Cai

et al.

Published: Dec. 27, 2024

Language: Английский

CPDM: Content-preserving diffusion model for underwater image enhancement DOI Creative Commons
Xiaowen Shi, Yuan‐Gen Wang

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 28, 2024

Underwater image enhancement (UIE) is challenging since degradation in aquatic environments complicated and changing over time. Existing mainstream methods rely on either physical-model or data-driven, suffering from performance bottlenecks due to changes imaging conditions training instability. In this article, we attempt adapt the diffusion model UIE task propose a Content-Preserving Diffusion Model (CPDM) address above challenges. CPDM first leverages as its fundamental for stable then designs content-preserving framework deal with conditions. Specifically, construct conditional input module by adopting both raw difference between noisy images at each time step of process, which can enhance model's adaptability considering involving underwater environments. To preserve essential content images, compensation content-aware extracting low-level features down block. We conducted tests LSUI, UIEB, EUVP datasets, results show that outperforms state-of-the-art subjective objective metrics, achieving best overall performance. The GitHub link code https://github.com/GZHU-DVL/CPDM.

Language: Английский

Citations

4
MSDBPN: multi-column smoothed dilated convolution based back projection network for stereo image super-resolution DOI
Zihao Zhou, Yongfang Wang, Junjie Lian

et al.

Pattern Analysis and Applications, Journal Year: 2025, Volume and Issue: 28(2)

Published: Feb. 24, 2025

Language: Английский

Citations

0
COLD-12: A Multi-Level Feature Extraction Hybrid CNN Model for Accurate Cotton Disease Diagnosis DOI Creative Commons
Md. Asraful Sharker Nirob, Prayma Bishshash, Abu Sayem Md. Siam

et al.

Franklin Open, Journal Year: 2025, Volume and Issue: unknown, P. 100263 - 100263

Published: April 1, 2025

Language: Английский

Citations

0
$$M^3$$SI-Net: a fusion model for facial emotion recognition with inception blocks and re-parameterized Swish1 function DOI

Sabyasachi Tribedi,

Ranjit Kumar Barai

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Language: Английский

Citations

0
Knowledge Distillation and Parameter Simplification for Power Operation and Maintenance-based LLMs DOI
Jing Fu,

Huaxi Wu,

Han Cai

et al.

Published: Dec. 27, 2024

Language: Английский

Citations

0