[2603.19563] Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.19563 (cs) [Submitted on 20 Mar 2026] Title:Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search Authors:Haoyu Zhang, Zhihao Yu, Rui Wang, Yaochu Jin, Qiqi Liu, Ran Cheng View a PDF of the paper titled Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search, by Haoyu Zhang and 4 other authors View PDF HTML (experimental) Abstract: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. We build a hybrid supernet that integrates Vision State Space and Vision Transformer (VSS-ViT) modules, and optimize it with a Cross-Architecture Dual-Domain Knowledge Distillation (CA-DDKD) strategy. By coupling the computational efficiency of VSS blocks with the semantic expressiveness of ViT modules, CA-DDKD improves the representational capacity of the shared supernet and enhances ranking consistency, enabling reliable fitness estimatio...