Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning for Few-Shot Image-to-Image Translation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use noise-tolerant iterative pseudo-labeling instead of NTS (ablation) | Semi-supervised labeling on Animals-69 · Animals-69, 10% labeled | error rate: 18.3% vs. 15.2% | Helped |
| Add entropy regulation (ablation) | SEMIT image translation · Image-to-image translation, varying labeled-data percentages | mFID | Helped |
| Add OctConv layers (ablation) | SEMIT image translation · Image-to-image translation, varying labeled-data percentages | mFID | Helped |
| Add cycle consistency (ablation) | SEMIT image translation · Image-to-image translation, especially 10%-30% labeled data | mFID | Helped |
| Add semi-supervised learning (ablation) | SEMIT image translation · Image-to-image translation, especially 10%-30% labeled data | mFID | Helped |
| Set OctConv high- and low-frequency channel proportions to 0.5 each (ablation) | SEMIT OctConv · Animals-69 and Birds, one-shot with 90% labeled data | performance | Helped |
| Add 20,000 unlabeled animal-face images during joint training (ablation) | SEMIT · Animals++ | mFID: 99.42 -> 88.62 | Helped |
| Add 6,033 unlabeled CUB-200-2011 bird images during joint training (ablation) | SEMIT · Birds++ | mFID: 128.4 -> 108.97 | Helped |
Closest papers by meaning
- Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images (AAAI 2022 · similarity 0.89)
- Few-Shot Incremental Learning for Label-to-Image Translation (CVPR 2022 · similarity 0.89)
- TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning (CVPR 2020 · similarity 0.88)
- LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data (CVPR 2023 · similarity 0.87)
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020 · similarity 0.87)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.86)
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.