AI Paper Atlas

Research map / Detection and segmentation / Tracking

Tracking by Instance Detection: A Meta-Learning Approach

Guangting Wang, Chong Luo, Xiaoyan Sun, Zhiwei Xiong, Wenjun Zeng

CVPR 2020 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 190 citations (OpenAlex)

Check 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 MAML initialization rather than standard detector training, then adapt on the initial frame (ablation)FCOS detector · OTB-100AUC: 0.464 -> 0.671Improved
Add kernel-wise learnable learning rates to both classification and regression branches (ablation)FCOS-MAML · OTB-100AUC: 0.628 -> 0.704Improved
Add KLLR to the classification branch (ablation)FCOS-MAML · OTB-100AUC: 0.628 -> 0.661Improved
Add KLLR to the regression branch (ablation)FCOS-MAML · OTB-100AUC: 0.628 -> 0.676Improved
Online-update both classification and regression branches instead of only classification (ablation)FCOS-MAML · LaSOTAUC: 0.523 -> 0.496Hurt
Online-update both classification and regression branches instead of only classification (ablation)FCOS-MAML · VOT-2018EAO: 0.394 -> 0.392No clear effect
Online-update the classification branch rather than omitting online updating (ablation)FCOS-MAML · OTB-100AUC: 0.671 -> 0.690Improved
Share block-4 between classification and regression branches (ablation)FCOS-MAML · OTB-100AUC: 0.704 -> 0.712No clear effect
Replace ResNet-18 with ResNet-50 (ablation)FCOS-MAML · VOT-2018EAO: 0.392 -> 0.444Improved
Replace ResNet-18 with ResNet-50 (ablation)FCOS-MAML · TrackingNetAUC: 0.757 -> 0.758No clear effect
Use FCOS-MAML instead of DiMP-18TrackingNet · TrackingNetAUC: 0.723 -> 0.757Improved
Use FCOS-MAML instead of DiMP-18LaSOT-test · LaSOT-testAUC: 0.532 -> 0.523Hurt

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