AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Learning More Universal Representations for Transfer-Learning

Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot, Mohamed El Amine Seddik, Mohamed Tamaazousti

TPAMI 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 66 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 FSFT to MulDiP-Net (ablation)MulDiP-Net · 8 target datasets (ILSVRC*)mNRG: +7.9 -> +10.7Improved
use FSFT instead of SFT (different learning rates for first and last layers) (ablation)self fine-tuning · 8 target datasets (ILSVRC*)mNRG: -0.1 -> +4.5Improved
use FSFT instead of frozen self-training FrST (ablation)self-training · 8 target datasets (ILSVRC*)mNRG: -11.6 -> +4.5Improved
use FSFT as dimensionality reduction (DR) rather than full FSFT (ablation)FSFT · 8 target datasets (ILSVRC*)mNRG: +4.5 -> +3.4Hurt
use FSFT as dimensionality reduction within MulDiP (ablation)MulDiP+FSFT · 8 target datasets (ILSVRC*)mNRG: +10.7 -> +8.8Hurt
MulDiP-Net instead of ensemble of networksMulDiP-Net · 8 target datasets (ILSVRC*)mNRG: +2.3 -> +7.9Improved
MulDiP-Net instead of multi-task learningMulDiP-Net · 8 target datasets (ILSVRC*)mNRG: -16.2 -> +7.9Improved
MulDiP-Net instead of multi-label learningMulDiP-Net · 8 target datasets (ILSVRC*)mNRG: -45.0 -> +7.9Improved
MulDiP-Net instead of recursive learningMulDiP-Net · 8 target datasets (ILSVRC*)mNRG: -4.8 -> +7.9Improved
MulDiP+FSFT instead of MuCaLe-NetMulDiP+FSFT · 10 target datasetsmNRG: +7.7 -> +9.8Improved
add MulDiP-Net to Net-S with VGG-16 (ablation)Net-S VGG-16 · 8 target datasets, full ILSVRCmNRG: +44.8 -> +55.3Improved
add MulDiP-Net to Net-S with DarkNet-20 (ablation)Net-S DarkNet-20 · 8 target datasets, full ILSVRCmNRG: +38.9 -> +47.1Improved

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