AI Paper Atlas

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

Deep Feature Space: A Geometrical Perspective

Ioannis Kansizoglou, Loukas Bampis, Antonios C. Gasteratos

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 62 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
train fusion model on held-out half D_2 instead of data used for extractors (S_a-a -> S_1-2), DNN (ablation)fusion model · RML + BAUM-1smean accuracy (%): 55.64 -> 61.46Improved
same change with SVM fusion (ablation)fusion model · RML + BAUM-1smean accuracy (%): 59.62 -> 64.05Improved
same change with extractors pre-trained on AffectNet/IEMOCAP (S'_a-a -> S'_1-2) (ablation)DNN fusion · RML + BAUM-1smean accuracy (%): 65.18 -> 68.98Improved
add L2 normalisation (L2-Softmax s=20) to Softmax (ablation)CNN on CIFAR · CIFAR feature spaceseparability S_R: .990 -> .845Hurt
lower L2-Softmax scale s from 20 to 0.1 (ablation)L2-Softmax · CIFAR feature spaceseparability S_R: .845 -> .588Hurt
replace Softmax with L2-Softmax s=0.1 (ablation)CNN on CIFAR · CIFAR feature spaceloss-ratio L_R: 2.63 -> 19.52Hurt
replace Softmax with SphereFace (ablation)CNN on CIFAR · CIFAR feature spacecentrality C_R: .859 -> .949Improved
replace Softmax with SphereFace (ablation)CNN on CIFAR · CIFAR feature spaceloss-ratio L_R: 2.63 -> 1.24Improved
replace Softmax with L-Softmax (ablation)CNN on CIFAR · CIFAR feature spaceloss-ratio L_R: 2.63 -> 1.42Improved
use fusion training strategy S_1-2 vs S_1-1 (DNN)fusion model · RML + BAUM-1smean accuracy (%): 58.53 -> 61.46Improved
swap DNN fusion for SVM fusion under S_a-afusion model · RML + BAUM-1smean accuracy (%): 55.64 -> 59.62Improved
S_a-a vs S_1-2 on speaker s_3 (extractor already well generalised) (ablation)fusion strategy · RML s_3 DNNaccuracy (%): 70.07 -> 73.05Hurt

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