Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
On the Importance of Firth Bias Reduction in Few-Shot Classification
Saba Ghaffari, Ehsan Saleh, David Forsyth, Yu-Xiong Wang
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 Firth bias reduction | DC · Cross-dataset few-shot classification on CUB, mini-ImageNet and tiered-ImageNet features | accuracy: 0.26 ± 0.03; 1.00 ± 0.04; 0.15 ± 0.03; 1.12 ± 0.03; 0.15 ± 0.04; 0.43 ± 0.02; 0.01 ± 0.01; 0.90 ± 0.02 | Improved |
| Add Firth bias reduction | DC on tiered-ImageNet · 10-way and 15-way, 1-shot and 5-shot, no artificial samples | accuracy: 0.63 ± 0.04; 0.33 ± 0.03; 0.67 ± 0.03; 0.46 ± 0.03 | Improved |
| Replace uniform Firth prior with the imbalanced class-frequency prior (ablation) | Firth-penalized logistic classifier · Imbalanced mini-ImageNet few-shot classification | accuracy | Hurt |
| Use L2 regularization instead of Firth bias reduction (ablation) | Few-shot logistic classifier · mini-ImageNet, across reported shots and feature backbones | accuracy | No clear effect |
| Use confidence-penalty label smoothing instead of Firth bias reduction (ablation) | Logistic classifier with ResNet-10 · Few-shot classification, 5-, 10-, and 15-shot | accuracy improvement: 5-shot: 0.13 ± 0.13 % vs 0.23 ± 0.06 %; 10-shot: 0.52 ± 0.14 % vs 0.73 ± 0.07 %; 15-shot: 0.57 ± 0.18 % vs 1.00 ± 0.07 % | Hurt |
| Use unigram label smoothing instead of Firth bias reduction (ablation) | Few-shot logistic classifier · Few-shot image classification | accuracy | Hurt |
| Add Firth bias reduction | Cosine classifier · mini-ImageNet, tiered-ImageNet, and CIFAR-FS; 5- and 10-shot | accuracy: more than 2.5% | Improved |
Closest papers by meaning
- Benchmarking Spurious Bias in Few-Shot Image Classifiers (ECCV 2024 · similarity 0.90)
- MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation (ICLR 2024 · similarity 0.86)
- Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels (AAAI 2025 · similarity 0.85)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.85)
- AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning (CVPR 2024 · similarity 0.85)
- Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning (CVPR 2024 · similarity 0.85)
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.
