Research map / Label-efficient and robust learning / Semi-supervised learning
LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-light Image Enhancement
Ye Yu, Fengxin Chen, Jun Yu, Zhen Kan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add mean-teacher-assisted GP regression loss to basic mean-teacher (ablation) | LMT-GP · LOL | PSNR: 22.73 -> 24.12 | Improved |
| use constant-covariance variant of GPR loss instead of full L_gpr (ablation) | LMT-GP · LOL | PSNR: 23.55 -> 24.12 | Improved |
| add pseudo-label adaptation module (PAM) (ablation) | LMT-GP · LOL | PSNR: 21.54 -> 24.12 | Improved |
| select PAM latent vectors by PSNR instead of SSIM (ablation) | PAM · LOL | PSNR: 22.65 -> 24.12 | Improved |
| add perceptual loss (ablation) | LMT-GP · LOL | PSNR: 21.66 -> 24.12 | Improved |
| add SSIM loss (ablation) | LMT-GP · LOL | PSNR: 23.87 -> 24.12 | Improved |
| add unlabeled loss (ablation) | LMT-GP · LOL | SSIM: PSNR 23.85 -> 24.12, SSIM 0.906 -> 0.902 | Mixed |
| use LMT-GP-enhanced images as preprocessing for night segmentation | HRNet on ACDC · ACDC | mIoU: 31.66 -> 39.33 | Improved |
| use LMT-GP preprocessing for face detection | YOLOv5 on Darkface · Darkface | mAP (%): 40.47 -> 43.92 | Improved |
| apply EnGAN as preprocessing for face detection | YOLOv5 on Darkface · Darkface | mAP (%): 40.47 -> 37.34 | Hurt |
Closest papers by meaning
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.87)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.86)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.85)
- Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration (CVPR 2025 · similarity 0.85)
- Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement (AAAI 2024 · similarity 0.84)
- Efficient Diffusion as Low Light Enhancer (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
