AI Paper Atlas

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

Long Short-Term Sample Distillation

Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi

AAAI 2020 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 8 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
use long-term and short-term sample-specific teachers togetherLSTSD · CIFAR100accuracy (%): 69.42 vs. 68.37; 71.51 vs. 70.26; 73.17 vs. 72.00; 73.83 vs. 72.57; 79.35 vs. 78.83Improved
use long-term and short-term sample-specific teachers togetherLSTSD with BERT · RTE, MRPC, SST-2accuracy (%): 74.73 vs. 74.01; 89.22 vs. 87.25; 93.35 vs. 93.12Improved
use long-term and short-term sample-specific teachers togetherLSTSD with BERT · CoLAMatthews correlation (%): 61.59 vs. 61.75No clear effect
use long-term and short-term sample-specific teachers togetherLSTSD with CNN · RTE, SST-2, CoLAaccuracy or Matthews correlation (%): 57.40 vs. 56.68; 72.36 vs. 71.67; 14.50 vs. 12.81Improved
use long-term and short-term sample-specific teachers togetherLSTSD with CNN · MRPCaccuracy (%): 73.28 vs. 73.77Hurt
add the long-term teacher (ablation)LSTSD · CIFAR100, ResNet-20accuracy (%): 69.09 -> 69.42Improved
add the short-term teacher (ablation)LSTSD · CIFAR100, ResNet-20accuracy (%): 68.82 -> 69.42Improved
use numerous sample-specific teachers instead of shared teachers (ablation)LSTSD · CIFAR100, ResNet-20accuracy (%): 67.85 -> 69.42Improved
increase mini-generation length from 1 to 6 epochs (ablation)LSTSD · CIFAR100, ResNet-20accuracyImproved
increase mini-generation length beyond 6 epochs toward 40 (ablation)LSTSD · CIFAR100, ResNet-20accuracyHurt

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