AI Paper Atlas

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

Worst Case Matters for Few-Shot Recognition

Minghao Fu, Yun-Hao Cao, Jianxin Wu

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-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 stability regularization (SR) on top of AC (ablation)AC fine-tuning, WRN-28-10 · mini-ImageNet 5-way 1-shotACC_1: 36.80 -> 40.52Improved
add stability regularization (SR) on top of AC (ablation)AC fine-tuning, ResNet-18 · mini-ImageNet 5-way 1-shotACC_1: 25.60 -> 32.00Improved
add ensemble of SR (EnSR) on top of SR (ablation)AC+SR, WRN-28-10 · mini-ImageNet 5-way 1-shotACC_m: 69.38 -> 69.59Improved
add adaptability calibration alone (fine-tune res5) (ablation)ResNet-18 baseline · mini-ImageNet 5-way 1-shotACC_1: 30.42 -> 25.60Hurt
add adaptability calibration alone (fine-tune res5) (ablation)ResNet-18 baseline · mini-ImageNet 5-way 5-shotACC_m: 73.61 -> 78.58Improved
add adaptability calibration alone (ablation)WRN-28-10 baseline · mini-ImageNet 5-way 1-shotACC_m: 67.86 -> 67.36Hurt
add AC+SR to Baseline pretraining (ablation)Baseline-pretrained ResNet-18 · mini-ImageNet 5-way 1-shotACC_1: 18.42 -> 21.86Improved
add AC+SR to Baseline pretraining (ablation)Baseline-pretrained ResNet-18 · mini-ImageNet 5-way 1-shotACC_m: 50.37 -> 50.27No clear effect
add AC+EnSR to Baseline pretraining (ablation)Baseline-pretrained ResNet-18 · mini-ImageNet 5-way 1-shotACC_m: 50.37 -> 54.42Improved
add AC+EnSR to Baseline++ pretraining (ablation)Baseline++-pretrained ResNet-18 · mini-ImageNet 5-way 5-shotACC_1: 49.08 -> 56.80Improved
fine-tune more residual groups (res5+res4+res3+res2+1) instead of res5 only (ablation)AC+EnSR, ResNet-18 · mini-ImageNet 5-way 1-shotACC_1: 32.78 -> 25.60Hurt
fine-tune res5+res4+res3 instead of res5 only (ablation)AC+EnSR, ResNet-18 · mini-ImageNet 5-way 1-shotACC_1: 32.78 -> 22.96Hurt

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