AI Paper Atlas

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

Prototype Rectification for Few-Shot Learning

Jinlu Liu, Liang Song, Yongqiang Qin

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot

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 intra-class bias diminishing (ablation)CSPN (WRN-28-10) · miniImageNet 1-shotaccuracy: 61.84 -> 69.81Improved
add intra-class bias diminishing (ablation)CSPN (WRN-28-10) · tieredImageNet 1-shotaccuracy: 69.20 -> 78.12Improved
add intra-class bias diminishing (ablation)CSPN (WRN-28-10) · miniImageNet 5-shotaccuracy: 78.64 -> 81.58Improved
add intra-class bias diminishing (ablation)CSPN (WRN-28-10) · tieredImageNet 5-shotaccuracy: 84.31 -> 86.67Improved
add cross-class bias diminishing (ablation)CSPN (WRN-28-10) · tieredImageNet 1-shotaccuracy: 69.20 -> 70.84Improved
add cross-class bias diminishing (ablation)CSPN (WRN-28-10) · miniImageNet 1-shotaccuracy: 61.84 -> 62.54Improved
add cross-class bias diminishing (ablation)CSPN (WRN-28-10) · miniImageNet 5-shotaccuracy: 78.64 -> 79.32Improved
add cross-class bias diminishing on top of intra-class (ablation)BD_i-CSPN · tieredImageNet 1-shotaccuracy: 78.12 -> 78.74Improved
add both bias diminishing modules (ablation)CSPN (ConvNet-128) · miniImageNet 1-shotaccuracy: 55.62 -> 61.74Improved
add both bias diminishing modules (ablation)CSPN (ResNet-12) · miniImageNet 5-shotaccuracy: 76.26 -> 79.23Improved
use BD-CSPN instead of Transductive Fine-TuningWRN-28-10 · miniImageNet 1-shotaccuracy: 65.73 -> 70.31Improved
use BD-CSPN instead of Transductive Fine-TuningResNet-12 · miniImageNet 5-shotaccuracy: 74.53 -> 79.23Improved

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