Pith. sign in

REVIEW

Self-Supervised Multi-Object Tracking For Autonomous Driving From Consistency Across Timescales

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.13147 v2 pith:VXWN323C submitted 2023-04-25 cs.CV

classification cs.CV
keywords self-supervisedlearningre-identificationautonomousdrivingfeaturesframemethods
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short compared to their supervised counterparts. We hypothesize that this drawback results from formulating self-supervised objectives that are limited to single frames or frame pairs. Such formulations do not capture sufficient visual appearance variations to facilitate learning consistent re-identification features for autonomous driving when the frame rate is low or object dynamics are high. In this work, we propose a training objective that enables self-supervised learning of re-identification features from multiple sequential frames by enforcing consistent association scores across short and long timescales. We perform extensive evaluations demonstrating that re-identification features trained from longer sequences significantly reduce ID switches on standard autonomous driving datasets compared to existing self-supervised learning methods, which are limited to training on frame pairs. Using our proposed SubCo loss function, we set the new state-of-the-art among self-supervised methods and even perform on par with fully supervised learning methods.

Discussion (0). Continue with ORCID to comment.

Pith tools