Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning
Hao Zhu, Piotr Koniusz
Check 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 |
|---|---|---|---|
| Learn the EASE discriminant subspace and use SIAMESE clustering | ResNet-12 few-shot inference · mini-ImageNet, transductive 1-shot | accuracy: 67.19 ± 0.55 -> 70.47 ± 0.30 | Improved |
| Learn the EASE discriminant subspace and use SIAMESE clustering | ResNet-12 few-shot inference · tiered-ImageNet, transductive 1-shot | accuracy: 73.21 ± 0.58 -> 84.54 ± 0.27 | Improved |
| Use EASE+SIAMESE instead of the strongest listed method | WRN-28-10 few-shot inference · mini-ImageNet, transductive 1-shot | accuracy: 83.05 ± 0.79 -> 83.00 ± 0.21 | No clear effect |
| Use EASE+SIAMESE instead of iLCT | WRN-28-10 few-shot inference · tiered-ImageNet, transductive 1-shot | accuracy: 88.50 ± 0.75 -> 88.96 ± 0.23 | Improved |
| Add EASE to QR+SIAMESE (ablation) | ResNet-12 few-shot inference · CIFAR-FS, transductive 1-shot | accuracy: 75.46±0.26 -> 78.41±0.29 | Improved |
| Replace SIAMESE with Soft K-means (ablation) | EASE few-shot inference · mini-ImageNet, transductive 1-shot, ResNet-12 | accuracy: 70.47 ± 0.30 -> 57.00 ± 0.26 | Hurt |
| Replace EASE with QR matrix decomposition (ablation) | SIAMESE few-shot inference · mini-ImageNet, transductive 1-shot, ResNet-12 | accuracy: 70.47 ± 0.30 -> 68.66 ± 0.37 | Hurt |
| Use EASE+SIAMESE rather than Soft K-means for class estimation (ablation) | DenseNet few-shot inference · mini-ImageNet, transductive 1-shot | accuracy: 74.30 ± 0.26 -> 79.42 ± 0.27 | Improved |
| Add SIAMESE's support-label constraints to Sinkhorn K-means (ablation) | EASE features · few-shot benchmarks | accuracy: 0.3–0.4% | Improved |
| Use the proposed EASE+SIAMESE inference | ResNet-12 few-shot inference · mini-ImageNet, semi-supervised 1-shot | accuracy: 70.99±0.91 -> 73.90±0.29 | Improved |
| Use the proposed EASE+SIAMESE inference | WRN-28-10 few-shot inference · tiered-ImageNet, semi-supervised 1-shot | accuracy: 89.35±0.68 -> 90.08±0.62 | Improved |
| Increase the number of query samples (ablation) | EASE transductive inference · mini-ImageNet | accuracy | Improved |
Closest papers by meaning
- TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification (ECCV 2020 · similarity 0.88)
- Parameterless Transductive Feature Re-representation for Few-Shot Learning (ICML 2021 · similarity 0.88)
- Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning (CVPR 2024 · similarity 0.88)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.87)
- Transductive Zero-Shot and Few-Shot CLIP (CVPR 2024 · similarity 0.86)
- UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning (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.
