AI Paper Atlas

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

General Compression Framework for Efficient Transformer Object Tracking

Lingyi Hong, Jinglun Li, Xinyu Zhou, Shilin Yan, Pinxue Guo, Kaixun Jiang, Zhaoyu Chen, Shuyong Gao, Runze Li, Xingdong Sheng, Wei Zhang, Hong Lu and 1 more

ICCV 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 12 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 prediction guidance (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 62.8 -> 63.5Improved
add feature mimicking (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 62.8 -> 63.3Improved
add replacement training (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 62.8 -> 63.7Improved
combine prediction guidance, feature mimicking and replacement training (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 62.8 -> 65.2Improved
use random stage replacement instead of decoupled stage training (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 64.6 -> 65.2Improved
add progressive replacement (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 64.8 -> 65.2Improved
train 500 epochs instead of 300 (ablation)CompressTracker-4 · LaSOT (CompressTracker-4, OSTrack teacher)AUC: 65.2 -> 66.1Improved
initialize decoder from teacher instead of random (ablation)CompressTracker-4 · LaSOTAUC: 62.3 -> 62.8Improved
keep decoder trainable instead of frozen (ablation)CompressTracker-4 · LaSOTAUC: 62.6 -> 62.8Improved
initialize backbone by skipping layers of OSTrack instead of first 4 layers of MAE-B (ablation)CompressTracker-4 · LaSOTAUC: 59.9% -> 62.3%Improved
use even stage division instead of uneven (2,2,6,2) (ablation)CompressTracker-4 · LaSOTAUC: 62.7% -> 62.8%No clear effect
use CompressTracker instead of plain distillationCompressTracker-4 · LaSOTAUC: 63.8 -> 66.1Improved

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