AI Paper Atlas

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

Distilling Object Detectors with Global Knowledge

Sanli Tang, Zhongyu Zhang, Zhanzhan Cheng, Jing Lu, Yunlu Xu, Yi Niu, Fan He

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Knowledge distillation for detectors · 14 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 prototypes to DeFeat (distill weights) (ablation)DeFeat · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.0 -> 82.4Improved
add prototypes to RKD (ablation)RKD · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 81.6 -> 82.0Improved
add prototypes to Vanilla-KD (ablation)Vanilla-KD · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 81.8 -> 82.2Improved
add global knowledge to feature-based and response-based local knowledge (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.6 -> 82.9Improved
use global knowledge only versus local feature only (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.0 -> 82.4Improved
use PGM prototypes instead of K-Means on student features (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.3 -> 82.9Improved
use PGM prototypes instead of DBSCAN on teacher features (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.2 -> 82.9Improved
use representative prototypes instead of ambiguous instances (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 81.8 -> 82.9Improved
increase prototype update period T from 1 to 3 (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.9 -> 82.2Hurt
use K=10 prototypes instead of K=1 (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.0 -> 82.9Improved
raise lambda from 10 to 100 (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.9 -> 82.0Hurt
raise alpha3 from 5 to 20 (ablation)Ours · VOC, 1x schedule ablation (Res101 teacher, Res50 student)AP50: 82.9 -> 82.2Hurt

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