AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Discriminant Feature Extraction by Generalized Difference Subspace

Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi, Jing‐Hao Xue, Atsuto Maki

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 15 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 normalization of projected data to gFDA (ablation)gFDA · CMU Multi-PIE (128 subjects)EER (%): 4.65 -> 0.56Improved
add normalization of projected data to GDS projection (ablation)GDS projection · CMU Multi-PIE (128 subjects)EER (%): 8.59 -> 0.43Improved
add normalization of projected data to GDS projection (ablation)GDS projection · Yale face B+ (29 classes)EER (%): 15.72 -> 8.91Improved
add normalization of projected data to gFDA (ablation)gFDA · Yale face B+ (29 classes)EER (%): 11.43 -> 8.28Improved
add normalization to pcaLDA (ablation)pcaLDA · CMU Multi-PIE (128 subjects)recognition rate (%): 97.98 -> 97.90No clear effect
replace linear gFDA with kernel KgFDAgFDA · ALOI300 (mean over 2-4 learning images)mean recognition rate (%): 93.2 -> 93.9Improved
replace linear gFDA with kernel KgFDA on CNN featuresgFDA · ETH80 (CNN features, 5 objects for learning)recognition rate (%): 82.37 -> 92.08Improved
apply linear FDA/gFDA/GDS on top of fine-tuned CNN featuresResNet50 · ETH80 (CNN features, 5 objects for learning)recognition rate (%): 90.81 -> 90.56No clear effect
apply linear gFDA on top of ResNet18 featuresResNet18 · MNIST (CNN features)recognition rate (%): 99.17 -> 98.83Hurt
apply kernel KGDS on top of ResNet18 featuresResNet18 · MNIST (CNN features)recognition rate (%): 99.17 -> 99.61Improved
apply linear gFDA on top of ResNet50 featuresResNet50 · CIFAR10 (CNN features)recognition rate (%): 93.21 -> 91.84Hurt
apply kernel KGDS on top of ResNet50 featuresResNet50 · CIFAR10 (CNN features)recognition rate (%): 93.21 -> 93.92Improved

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