AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning

Han-Jia Ye, Hexiang Hu, De‐Chuan Zhan

IJCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 72 citations (OpenAlex)

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 changedWhereMeasuredEffect
add the neural dictionary (ablation)CASTLE- · Heterogeneous GFSLharmonic mean accuracy: 47.50 -> 49.05Improved
add the neural dictionary (ablation)CASTLE- · Office-Home GFSLharmonic mean accuracy: 33.73 -> 34.48Improved
adapt head classifiers conditioned on tail examples (aCASTLE)CASTLE · Heterogeneous GFSLharmonic mean accuracy: 49.05 -> 52.81Improved
adapt head classifiers conditioned on tail examples (aCASTLE)CASTLE · Office-Home GFSLharmonic mean accuracy: 34.48 -> 39.98Improved
adapt head classifiers conditioned on tail examples (aCASTLE)CASTLE · MiniImageNet GFSL 5-shotharmonic mean accuracy: 76.32 -> 78.33Improved
adapt head classifiers conditioned on tail examples (aCASTLE)CASTLE · MiniImageNet GFSL 1-shotharmonic mean accuracy: 66.22 -> 66.24No clear effect
add many-shot pre-training of the backbone (ablation)CASTLE · MiniImageNet 1-shot 5-way GFSLharmonic mean accuracy: 38.24 -> 66.22Improved
add many-shot pre-training of the backbone (ablation)CASTLE · MiniImageNet 1-shot 5-way FSLmean accuracy: 64.23 -> 66.83Improved
increase number of classifiers in multi-classifier training from 1 to 256 (ablation)CASTLE · MiniImageNet 1-shot 5-way GFSLharmonic mean accuracy: 64.53 -> 66.72Improved
average synthesized classifiers after synthesis (Post-AVG) instead of averaging embeddings (Pre-AVG) (ablation)CASTLE · MiniImageNet 5-shot 5-way GFSLharmonic mean accuracy: 76.32 -> 76.28No clear effect
add light-weight scale and bias fine-tuningaCASTLE · MiniImageNet 5-shot 5-way GFSLharmonic mean accuracy: 78.33 -> 78.93Improved
add light-weight scale and bias fine-tuningCASTLE · MiniImageNet 5-shot 5-way GFSLharmonic mean accuracy: 76.32 -> 76.43Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy