Research map / Label-efficient and robust learning / Semi-supervised learning
SEA-PACE: Semi-Supervised Underwater Image Enhancement via Gaussian Process–Assisted Self-Paced Learning
Jingyang Wang, Hengyue Bi, Jingchao Cao, Feng Gao, Junyu Dong
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 GPR-based uncertainty weighting (ablation) | Mean Teacher baseline · UIEB test | PSNR: 23.62 -> 24.28 | Improved |
| add GPR-based uncertainty weighting (ablation) | Mean Teacher baseline · U45 | URanker: 1.70 -> 1.89 | Improved |
| add rank-based reliability transformation (ablation) | Mean Teacher + GPR · UIEB test | PSNR: 24.28 -> 24.42 | Improved |
| add rank-based reliability transformation (ablation) | Mean Teacher + GPR · U45 | URanker: 1.89 -> 2.00 | Improved |
| add self-paced consistency learning (SPCL) (ablation) | Mean Teacher + MARE · UIEB test | PSNR: 24.42 -> 24.57 | Improved |
| add self-paced consistency learning (SPCL) (ablation) | Mean Teacher + MARE · U45 | URanker: 2.00 -> 2.07 | Improved |
| increase unlabeled data ratio from 1:1 to 1:4 (ablation) | SEA-PACE · UIEB test | PSNR: 24.47 -> 24.69 | Improved |
| SEA-PACE vs SemiUIR | SemiUIR · UIEB test | PSNR: 24.26 -> 24.57 | Improved |
| SEA-PACE vs best baselines on EUVP PSNR | HCLR-Net · EUVP test | PSNR: 26.31 -> 26.39 | Improved |
| SEA-PACE vs NU2Net on URanker | NU2Net · U45 | URanker: 2.12 -> 2.07 | Hurt |
| SEA-PACE vs ERD (supervised) on SUIM-E | ERD · SUIM-E test | PSNR: 23.78 -> 23.96 | Improved |
Closest papers by meaning
- Self-MAR: Self-Supervised Multi-Stage Autoregressive Model for Water-Related Optical Image Enhancement (TPAMI 2026 · similarity 0.89)
- Uncertainty Inspired Underwater Image Enhancement (ECCV 2022 · similarity 0.88)
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.88)
- Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement (AAAI 2024 · similarity 0.87)
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.86)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · 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.
