Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling
Ran Tao, Han Zhang, Yutong Zheng, Marios Savvides
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 DCM (feature normalization and a learnable scale vector) to support-set finetuning (ablation) | Finetuning backbone · Meta-Dataset, 10 datasets | accuracy | Improved |
| Add feature normalization (ablation) | Backbone finetuning · CU-Birds and Fungi | accuracy: 3.10\%; 3.39\% | Improved |
| Add a learnable scale vector after feature normalization (ablation) | Backbone finetuning with feature normalization · Meta-Dataset, 7 out of 10 datasets | accuracy | Improved |
| Add Selected Sampling to DCM-based finetuning (ablation) | Finetuning backbone with DCM · Meta-Dataset, all 10 datasets | accuracy: $0.34\%$ to $1.75\%$ | Improved |
| Finetune the backbone without DCM or Selected Sampling | Classifier-Baseline · Birds and Fungi | accuracy | Hurt |
| Use DCM+SS during backbone finetuning rather than the classifier baseline | ResNet18 and ResNet34 · Meta-Dataset, all 10 datasets | accuracy: $1.92\%$(mscoco) to $29.7\%$(Traffic sign) | Improved |
Closest papers by meaning
- Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning (AAAI 2021 · similarity 0.88)
- A Baseline for Few-Shot Image Classification (ICLR 2020 · similarity 0.88)
- From Channel Bias to Feature Redundancy: Uncovering the “Less is More” Principle in Few-Shot Learning (TPAMI 2026 · similarity 0.88)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.86)
- Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning (CVPR 2024 · similarity 0.86)
- Neural Fine-Tuning Search for Few-Shot Learning (ICLR 2024 · 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.
