Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Prototypes-oriented Transductive Few-shot Learning with Conditional Transport
Long Tian, Jingyi Feng, Xiaoqiang Chai, Wenchao Chen, Liming Wang, Xiyang Liu, Bo Chen
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 |
|---|---|---|---|
| replace PUTM with PT-MAP uniform-prior transport under class imbalance | transductive few-shot · miniImageNet 1-shot imbalanced (WRN) | accuracy (%): 70.9 -> 60.6 | Hurt |
| use PUTM with conditional transport instead of PT-MAP under class balance | transductive few-shot · miniImageNet 1-shot balanced (WRN) | accuracy (%): 78.9 vs 78.4 | No clear effect |
| use PUTM instead of BAVAR in class-imbalanced 1-shot | transductive few-shot · miniImageNet 1-shot imbalanced (WRN) | accuracy (%): 74.1 -> 70.9 | Hurt |
| self-supervised WRN features instead of standard WRN | PUTM · miniImageNet 1-shot imbalanced | accuracy (%): 70.9 -> 73.8 | Improved |
| calibrate prototypes with backward transport instead of forward transport (ablation) | PUTM · miniImageNet 5-way 1-shot imbalanced | accuracy (%) | Hurt |
| use PUTM instead of alpha-TIM for inference time | transductive few-shot · CUB 5-way 1-shot (RN18) | end-to-end time (s): 5.6 -> 2.9 | Improved |
Closest papers by meaning
- Realistic evaluation of transductive few-shot learning (NeurIPS 2021 · similarity 0.89)
- Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization (CVPR 2023 · similarity 0.86)
- Prototype Rectification for Few-Shot Learning (ECCV 2020 · similarity 0.86)
- Towards Practical Few-shot Query Sets: Transductive Minimum Description Length Inference (NeurIPS 2022 · similarity 0.86)
- BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning (AAAI 2024 · similarity 0.84)
- BECLR: Batch Enhanced Contrastive Few-Shot Learning (ICLR 2024 · similarity 0.83)
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.
