AI Paper Atlas

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

Distilled Siamese Networks for Visual Tracking

Jianbing Shen, Yuanpei Liu, Xingping Dong, Xiankai Lu, Fahad Shahbaz Khan, Steven C. H. Hoi

TPAMI 2021 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 165 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 TS (teacher-student) loss to hard-label training (ablation)DSTrpn student1 · OTB-100AUC: 0.429 -> 0.586Improved
add GT hard labels on top of TS loss (ablation)DSTrpn student1 · OTB-100AUC: 0.586 -> 0.579Hurt
replace GT with AH loss in GT+TS (ablation)DSTrpn student1 · OTB-100AUC: 0.579 -> 0.591Improved
add STR loss to TS (ablation)DSTrpn student1 · OTB-100AUC: 0.586 -> 0.608Improved
use AH+TS+STR full transfer instead of TS+STR (ablation)DSTrpn student1 · OTB-100AUC: 0.608 -> 0.624Improved
add STR loss to TS (ablation)DSTfc student1 · OTB-100AUC: 0.535 -> 0.548Improved
add STR weighting strategy (ablation)DSTrpn student1 (AH+TS+STR) · OTB-100AUC: 0.609 -> 0.624Improved
use proposed distillation loss instead of bounded loss (ablation)DSTrpn student1 · OTB-100AUC: 0.612 -> 0.624Improved
add knowledge sharing from intelligent student (TSsKD vs TSKD) (ablation)DSTrpn dim student · OTB-100AUC: 0.624 -> 0.646Improved
add knowledge sharing from intelligent student (TSsKD vs TSKD) (ablation)DSTfc dim student · OTB-100AUC: 0.557 -> 0.573Improved
add distillation (TSKD) to intelligent student trained on hard labels (ablation)SiamRPN student2 · OTB-100AUC: 0.630 -> 0.641Improved
train students with 25% gray images instead of 0% (ablation)DSTrpn · OTB-100AUC: 0.621 -> 0.646Improved

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