AI Paper Atlas

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

PARN: Position-Aware Relation Networks for Few-Shot Learning

Ziyang Wu, Yuwei Li, Lihua Guo, Kui Jia

ICCV 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 136 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
replace standard feature extractor with deformable one (DFE-4), 1-shot (ablation)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.64 -> 52.07Improved
replace standard feature extractor with deformable one (DFE-4), 5-shot (ablation)RN · Mini-ImageNet 5-way 5-shot5-way accuracy (%): 66.08 -> 67.53Improved
use DFE-4 instead of deeper SFE-6 with more parameters (ablation)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.74 -> 52.07Improved
deepen standard extractor from 4 to 6 layers (ablation)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.64 -> 51.74No clear effect
add self-correlation attention (SCA) (ablation)RN · Mini-ImageNet 5-way 5-shot5-way accuracy (%): 66.00 -> 67.14Improved
add cross-correlation attention (CCA) (ablation)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.29 -> 53.88Improved
add cross-correlation attention (CCA) (ablation)RN · Mini-ImageNet 5-way 5-shot5-way accuracy (%): 66.00 -> 69.49Improved
add both CCA and SCA (full DCA) (ablation)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.29 -> 54.36Improved
add both CCA and SCA (full DCA) (ablation)RN · Mini-ImageNet 5-way 5-shot5-way accuracy (%): 66.00 -> 70.50Improved
use CCA instead of SCA (ablation)RN with attention · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 52.64 -> 53.88Improved
add 1x1 convolution before RN (control) (ablation)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.64 -> 51.29No clear effect
add DFE and DCA together (full PARN)RN · Mini-ImageNet 5-way 1-shot5-way accuracy (%): 51.64 -> 55.22Improved

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