AI RESEARCH
Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search
arXiv CS.AI
•
ArXi:2603.19563v1 Announce Type: cross Modern computer vision requires balancing predictive accuracy with real-time efficiency, yet the high inference cost of large vision models (LVMs) limits deployment on resource-constrained edge devices. Although Evolutionary Neural Architecture Search (ENAS) is well suited for multi-objective optimization, its practical use is hindered by two issues: expensive candidate evaluation and ranking inconsistency among subnetworks. To address them, we propose EvoNAS, an efficient distributed framework for multi-objective evolutionary architecture search.