Papers › DEFT: Detection Embeddings for Tracking

DEFT: Detection Embeddings for Tracking

3 Feb 2021arXiv:2102.02267archive 2025-07-28

Mohamed Chaabane, Peter Zhang, J. Ross Beveridge, Stephen O'Hara

Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and appearance features to provide robustness to occlusions and other challenges, but typically this comes with the trade-off of a more complex and slower implementation. Recent successes on popular 2D tracking benchmarks indicate that top-scores can be achieved using a state-of-the-art detector and relatively simple associations relying on single-frame spatial offsets -- notably outperforming contemporary methods that leverage learned appearance features to help re-identify lost tracks. In this paper, we propose an efficient joint detection and tracking model named DEFT, or "Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints. DEFT has comparable accuracy and speed to the top methods on 2D online tracking leaderboards while having significant advantages in robustness when applied to more challenging tracking data. DEFT raises the bar on the nuScenes monocular 3D tracking challenge, more than doubling the performance of the previous top method. Code is publicly available.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

MedChaabane/DEFT officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Multi-Object TrackingMulti-Object TrackingMultiple Object TrackingObjectObject DetectionObject Trackingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Multi-Object Tracking nuScenes DEFT AMOTA 0.18 #104 of 115 Archive leaderboard report
Multi-Object Tracking MOT16 DEFT MOTA 68.03 #11 of 24 Archive leaderboard report
Multi-Object Tracking MOT17 DEFT MOTA 66.6 #39 of 48 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) DEFT HOTA 74.23 #14 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) DEFT MOTA 88.95 #14 of 34 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections