AI Paper Atlas

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

Distilling Knowledge From a Deep Pose Regressor Network

Muhamad Risqi U. Saputra, Pedro P. B. de Gusmao, Yasin Almalioglu, Andrew Markham, Niki Trigoni

ICCV 2019 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 130 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 hint training (HT) to the student (ablation)Student 72.88%, student loss · KITTI ablationATE (m): 80.842 -> 65.251Improved
replace HT with attentive hint training (AHT) (ablation)Student 72.88%, student loss · KITTI ablationATE (m): 65.251 -> 52.320Improved
replace student loss with attentive imitation loss (AIL) under HT (ablation)Student 72.88%, HT · KITTI ablationATE (m): 65.251 -> 36.459Improved
add both AHT and AIL versus HT with student loss (ablation)Student 72.88% · KITTI ablationATE (m): 65.251 -> 32.259Improved
add hint training (HT) to the student (ablation)Student 79.69%, student loss · KITTI ablationATE (m): 68.350 -> 53.661Improved
replace student loss with AIL under HT (ablation)Student 79.69%, HT · KITTI ablationATE (m): 53.661 -> 29.751Improved
replace HT with AHT under student loss (ablation)Student 79.69% · KITTI ablationATE (m): 53.661 -> 37.645Improved
add both AHT and AIL versus HT with student loss (ablation)Student 79.69% · KITTI ablationATE (m): 53.661 -> 25.857Improved
use AHT instead of HT for hint transfer (ablation)Student 72.88% · KITTI ablationhint reconstruction error: 0.0252 -> 0.0166Improved
add hint training to student with no HT (ablation)Student 72.88% · KITTI ablationhint reconstruction error: 0.6242 -> 0.0252Improved
use AIL+AHT distillation instead of supervised-only student at 92.95% reductionStudent d_rate 92.95% · KITTI Seq 09-10RMS ATE: 71.7517 -> 29.0294Improved
use proposed distillation instead of KD adapted to regressionStudent d_rate 92.95% · KITTI Seq 09-10RMS ATE: 165.2182 -> 29.0294Improved

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