Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Coarse-to-Fine Incremental Few-Shot Learning
Xiang Xiang, Yuwen Tan, Qian Wan, Jing Ma, Alan Yuille, Gregory D. Hager
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 contrastive MoCo base learning (ablation) | Knowe · BREEDS living17 | avg total accuracy: 40.10 -> 54.62 | Improved |
| add classifier-weight normalization (ablation) | Knowe · BREEDS living17 | avg total accuracy: 30.77 -> 54.62 | Improved |
| add classifier-weight normalization (ablation) | Knowe · BREEDS living17 | forgetting rate: 0.57 -> 0.33 | Improved |
| add freezing of memorized classifier weights (ablation) | Knowe · BREEDS living17 | avg total accuracy: 22.09 -> 54.62 | Improved |
| add freezing of memorized classifier weights (ablation) | Knowe · BREEDS living17 | forgetting rate: 0.66 -> 0.33 | Improved |
| add decoupling (freeze embedding weights) (ablation) | Knowe · BREEDS living17 | avg total accuracy: 50.66 -> 54.62 | No clear effect |
| add contrastive learning to fine-tuned coarse model without weight ops (ablation) | ResNet12 FT · CIFAR-100 (fine-tuning w/o IL) | now accuracy: ~25% -> ~35% | Improved |
| use Knowe instead of ANCOR fine-tuning | ResNet-50 · BREEDS living17 | avg total accuracy: 21.75 -> 54.62 | Improved |
| use Knowe instead of Weight Align+ | ResNet-50 · BREEDS entity30 | avg total accuracy: 41.78 -> 47.79 | Improved |
| use Knowe instead of Subsp. Reg.+ | ResNet12 · CIFAR-100 (C2FSCIL) | avg total accuracy: 33.00 -> 38.50 | Improved |
| use Knowe instead of ScaIL | ResNet12 · tieredImageNet (C2FSCIL) | avg total accuracy: 32.93 -> 33.24 | Improved |
| use Knowe incremental learning instead of joint training upper bound | ResNet-50 · BREEDS living17 | avg total accuracy: 54.62 vs 55.29 | No clear effect |
Closest papers by meaning
- Class-Incremental Learning With Strong Pre-Trained Models (CVPR 2022 · similarity 0.89)
- Class-Incremental Learning: A Survey (TPAMI 2024 · similarity 0.88)
- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (IJCV 2024 · similarity 0.87)
- Few-Shot Incremental Learning With Continually Evolved Classifiers (CVPR 2021 · similarity 0.87)
- Fine-Grained Angular Contrastive Learning With Coarse Labels (CVPR 2021 · similarity 0.87)
- Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning (CVPR 2025 · similarity 0.87)
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.
