AI Paper Atlas

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

Distilling Object Detectors via Monte Carlo Dropout

Junfei Yi, Hui Zhang, Jianxu Mao, Tengfei Liu, Mingjie Li, Sihao Lin, Hanyu Gu, Zhihui Li, Xiaojun Chang, Yaonan Wang

TPAMI 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Knowledge distillation for detectors · 9 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 MC-dropout teacher knowledge uncertainty (N=10)FGD · GFL Res101 to Res50 COCOmAP: 43.4 -> 44.1Improved
increase MC dropout samples N from 10 to 15 (ablation)FGD+Ours · GFL COCOmAP: 44.1 -> 43.8Hurt
use a single dropout sample (N=1) (ablation)FGD+Ours · GFL COCOmAP: 43.4 -> 43.9Improved
vary dropout ratio strategy a, b, c (ablation)FGD+Ours · GFL COCOmAP: 44.0 -> 44.0No clear effect
add uncertainty to teacher knowledge only (ablation)FGD · GFL COCOmAP: 43.4 -> 44.0Improved
add uncertainty to student knowledge only (ablation)FGD · GFL COCOmAP: 43.4 -> 43.6Improved
add uncertainty to both teacher and student (ablation)FGD+Ours · GFL COCOmAP: 44.0 -> 44.0No clear effect
add residual structure to uncertainty injection (ablation)FGD+Ours teacher side · GFL COCOmAP: 43.5 -> 44.0Improved
add uncertainty to feature KD MGDMGD · GFL 1x COCOmAP: 42.1 -> 43.0Improved
add uncertainty to feature KD PKDPKD · GFL 1x COCOmAP: 42.5 -> 42.6Improved
add uncertainty to logit KD LDLD · GFL 1x COCOmAP: 41.0 -> 41.2Improved
add uncertainty to FGD on Res18 studentFGD · GFL Res18 student COCOmAP: 33.3 -> 37.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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