AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow

Orcun Cetintas, Tim Meinhardt, Guillem Brasó, Laura Leal-Taixé

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 5 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 low-confidence detection boxes without GNN_node filtering (ablation)SPAM graph tracker · MOT17 val halfHOTA: 59.9 -> 58.5Hurt
add GNN_node detection-filtering level on top of low-confidence boxes (ablation)SPAM graph tracker · MOT17 val halfHOTA: 58.5 -> 60.4Improved
retrain model on its own pseudo-labels after synthetic pretraining (ablation)SPAM labeler · MOT17 val (ByteTrack trained on labels)HOTA: 49.6 -> 50.5Improved
add uncertainty-based active learning with 3.3% manual effort (ablation)SPAM labels · MOT17 val (ByteTrack trained on labels)HOTA: 50.5 -> 52.5Improved
pseudo-label retraining on real data (zero human effort) (ablation)SPAM · MOT17, MOT20, DanceTrackHOTA/MOTA/IDF1: +4-6 HOTA, +4-6 MOTA, +4-7 IDF1Improved
box-level graph-based active learning instead of image-level or random labeling (ablation)SPAM active learning · MOT17 valHOTA gain over no-AL baseline: 1.2 points from OracleImproved
use Coreset (diversity) selection instead of uncertainty-based selection (ablation)SPAM active learning · MOT17 valHOTA gainHurt
train detector on real instead of synthetic data (ablation)tracking components · MOT17/MOT20/DanceTrackHOTA: 9.9 HOTAImproved
train reID on real instead of synthetic data (ablation)tracking components · MOT17/MOT20/DanceTrackHOTANo clear effect
train association on real instead of synthetic data (ablation)tracking components · MOT17/MOT20/DanceTrackHOTA: +2.1 HOTAImproved
SPAM labels at 3.3% effort vs ground truth on harder datasetsByteTrack and GHOST · MOT20 and DanceTrack testHOTA: ByteTrack DanceTrack 39.5 vs 41.0 (GT)Mixed

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