AI Paper Atlas

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

Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition

Shiming Ge, Kangkai Zhang, Haolin Liu, Yingying Hua, Shengwei Zhao, Xin Jin, Hao Wen

AAAI 2020 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 32 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 a high-accuracy ResNet assistant (OUR-32-R) instead of lower-accuracy VGG assistant (ablation)OUR-16 student · CIFAR100 testaccuracy (%): 69.87 -> 74.65Improved
HORKD 16x16 student vs KD baseline at 32x32low-res classification · CIFAR100 testaccuracy (%): 74.26 -> 74.65Improved
reduce input resolution 32x32 to 16x16HORKD student · CIFAR100 testaccuracy (%): 77.76 -> 74.65Hurt
HORKD vs SKD at 32x32 on LFWlow-res face verification · LFWaccuracy (%): 89.72 -> 93.83Improved
HORKD vs SKD at 16x16 on LFWlow-res face verification · LFWaccuracy (%): 85.87 -> 90.03Improved
HORKD vs SKD on UCCS 16x16low-res face identification · UCCStop-1 error (%): 32.75 -> 22.19Improved
add cross-structure distillation stage (assistant) before cross-resolution (ablation)cross-resolution metric learning · metric learningaccuracy: +3.03%Improved
reduce student input resolution from 256 to 96 (ablation)OUR-R student · Cars196score: 82.23 -> 73.41Hurt
HORKD student (ResNet18, 256) vs ResNet50 teachermetric learning · Cars196 / CUB2011 / SOPscore: 75.91 -> 82.23 (Cars196)Mixed
add highest-order terms (use all L1+L2+L3+LC) vs without L1 (ablation)relational distillation loss · low-res face recognition (32x32)accuracyHurt
increase order of relational loss terms (ablation)relational distillation loss · low-res face recognition (32x32)accuracyImproved
distill directly cross-resolution without assistant stage (ablation)metric learning student · metric learningaccuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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