Which Objects Stay? Learning Hierarchical Persistence Beliefs for Lifelong Open-Vocabulary Object Maps
Overview
This research presents HiPer, a hierarchical persistence filter that learns object survival probabilities directly from data without relying on semantic categories. By retrieving visually and geometrically similar training instances, HiPer initializes a conjugate Beta belief over an object's survival probability and updates it using detections and missed observations. When an object is re-identified at a new location, its persistence belief transfers with the object, enabling the system to learn object-specific mobility over time. Experiments on 120 held-out simulated sequences show that HiPer consistently outperforms competing methods, with retrieval-based priors surpassing CLIP-derived label priors. Results on 47 held-out 3RScan environments further demonstrate that the proposed approach exceeds state-of-the-art baselines in real-world settings.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · simulated sequences: 120 other · reported trials
“When an object is re-identified at a new location, its persistence belief is transferred with the object, enabling the map to learn object-specific mobility over time. Experiments on 120 held-out simulated sequences show that HiPer consistently achieves the best performance among competing methods. Retrieval-based priors outperform CLIP-derived label priors, and object-specific online learning provides further gains.”
Exact source · revision 1Source owner not reported
Reported quantity · environments: 47 other · reported trials
“Results on 47 held-out 3RScan environments demonstrate that the proposed retrieval-based prior also outperforms state-of-the-art baselines in real-world settings.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalWhich Objects Stay? Learning Hierarchical Persistence Beliefs for Lifelong Open-Vocabulary Object Maps
This research presents HiPer, a hierarchical persistence filter that learns object survival probabilities directly from data without relying on semantic categories. By retrieving visually and geometrically similar training instances, HiPer initializes a conjugate Beta belief over an object's survival probability and updates it using detections and missed observations. When an object is re-identified at a new location, its persistence belief transfers with the object, enabling the system to learn object-specific mobility over time. Experiments on 120 held-out simulated sequences show that HiPer consistently outperforms competing methods, with retrieval-based priors surpassing CLIP-derived label priors. Results on 47 held-out 3RScan environments further demonstrate that the proposed approach exceeds state-of-the-art baselines in real-world settings.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).