Publication
Box it and Track it: A Weakly Supervised Framework for Cell Tracking
Nabeel Khalid; Mohammadmahdi Koochali; Khola Naseem; Gillian Lovel; Daniel A Porto; Biana Migliori; Johan Trygg; Andreas Dengel; Sheraz Ahmed
In: DAGM German Conference on Pattern Recognition, Freiburg. Annual Symposium of the German Association for Pattern Recognition (DAGM-2025), September 24-26, Freiburg, Germany, Springer Nature, 2025.
Abstract
Accurate cell tracking in microscopy is essential for studying biological dynamics like proliferation and migration. Traditional fully supervised methods demand dense pixel-wise masks for every frame, making them impractical for large-scale use. Recent methods like SAT reduce annotation effort by using sparse point-based supervision, but still require multiple positive and negative points per cell, which remains labor-intensive. BoxTrack offers a lightweight and annotation-efficient alternative, requiring only a single bounding box per cell in the first frame. Without relying on any point-level annotations, it performs end-to-end instance segmentation and tracking over entire sequences. This simplification leads to a substantial reduction in annotation cost while improving performance over SAT. On the CTMC dataset, BoxTrack improves Multiple Object Tracking Accuracy (MOTA) by \textbf{+15.96\%} over SAT. For the CTC dataset, it yields a \textbf{+8.86\%} MOTA gain. Code is available at \url{https://github.com/nabeelkhalid92/Box-it-Track-it}.