AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Knowledge Extraction with No Observable Data

Jaemin Yoo, Minyong Cho, Taebum Kim, U Kang

NeurIPS 2019 · Label-efficient and robust learning › Knowledge distillation · approach: Self and data-free distillation · 61 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
fine-tune Tucker student with KEGNET-generated dataTucker-compressed student · Pendigitsaccuracy: 26.44% -> 82.62 ± 1.05%Improved
fine-tune Tucker student with KEGNET-generated dataTucker-compressed student · SVHN Student 2accuracy: 11.02% -> 87.26 ± 0.46%Improved
fine-tune Tucker student with KEGNET-generated dataTucker-compressed student · Fashion MNIST Student 3accuracy: 46.55% -> 79.95 ± 1.36%Improved
use KEGNET data instead of Gaussian samplesT+Gaussian · MNIST Student 3accuracy: 71.76 ± 0.18% -> 89.94 ± 0.08%Improved
use KEGNET data instead of uniform random samplesT+Uniform · Letteraccuracy: 62.50 ± 0.90% -> 77.73 ± 0.33%Improved
fine-tune Tucker student with random Uniform/Gaussian dataTucker-compressed student · Fashion MNISTaccuracy: < 65.09% for Student 1Hurt
fine-tune Tucker student with random Uniform/Gaussian dataTucker-compressed student · MNIST Student 1accuracy: 85.18% -> 95.48 ± 0.11%Improved
fine-tune Tucker student with random noise on complex datasetsTucker-compressed student · SVHN Student 3accuracy: 11.07% -> 23.83 ± 1.86%Mixed
add decoder loss and diversity loss to generator objective (ablation)KEGNET generator · image datasetsdata diversityImproved

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