AI Paper Atlas

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

Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification

Wen-Hsuan Chu, Yu-Jhe Li, Jing-Cheng Chang, Yu-Chiang Frank Wang

CVPR 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 88 citations (OpenAlex)

Check 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
Use maximum-entropy patch sampling with Ours-FC instead of the fully connected baselineConv-4 few-shot classifier · Omniglot 5-Way 1-Shotaccuracy: 5.5%Improved
Use maximum-entropy patch sampling with Ours-CS instead of the cosine-similarity baselineConv-4 few-shot classifier · Omniglot 5-Way 1-Shotaccuracy: 4.2%Improved
Use maximum-entropy patch sampling with Ours-FC instead of the fully connected baselineConv-4 few-shot classifier · Omniglot 5-Way 5-Shotaccuracy: 0.5%Improved
Use maximum-entropy patch sampling with Ours-CS instead of the cosine-similarity baselineConv-4 few-shot classifier · Omniglot 5-Way 5-Shotaccuracy: 0.3%Improved
Use maximum-entropy patch sampling with Ours-FC instead of the fully connected baselineConv-4 few-shot classifier · miniImagenet 5-Way 1-Shotaccuracy: 5.1%Improved
Use maximum-entropy patch sampling with Ours-CS instead of the cosine-similarity baselineConv-4 few-shot classifier · miniImagenet 5-Way 1-Shotaccuracy: 4.2%Improved
Use maximum-entropy patch sampling with Ours-FC instead of the fully connected baselineConv-4 few-shot classifier · miniImagenet 5-Way 5-Shotaccuracy: 4.9%Improved
Use maximum-entropy patch sampling with Ours-CS instead of the cosine-similarity baselineConv-4 few-shot classifier · miniImagenet 5-Way 5-Shotaccuracy: 3.8%Improved
Add cosine-similarity classification instead of a fully connected classifierBaseline few-shot models · Omniglot 5-WayaccuracyImproved
Add cosine-similarity classification instead of a fully connected classifierBaseline few-shot models · miniImagenet 5-WayaccuracyImproved
Add soft voting over predictions, increasing votes from N=1 to N=3 (ablation)Ours on miniImagenet · miniImagenet 5-Way 5-Shotaccuracy: 3% to 4%Improved
Add soft voting over predictions, increasing votes from N=1 to N=3 (ablation)Ours on miniImagenet · miniImagenet 5-Way 1-Shotaccuracy: 2% to 3%Improved

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