{"ID":2854830,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15026","arxiv_id":"2510.15026","title":"MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning","abstract":"Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object detection and segmentation. However, their high computational cost limits adoption on resource-constrained platforms. We first examine the limitations of existing architectures in enabling efficient edge deployment without compromising performance. We then introduce MOBIUS, a family of foundation models for universal instance segmentation, designed for Pareto-optimal downscaling to support deployment across devices ranging from high-end accelerators to mobile hardware. To reduce training and inference demands, we propose: (i) a bottleneck pixel decoder for efficient multi-scale and multi-modal fusion, (ii) a language-guided uncertainty calibration loss for adaptive decoder pruning, and (iii) a streamlined, unified training strategy. Unlike efficient baselines that trade accuracy for reduced complexity, MOBIUS reduces pixel and transformer decoder FLOPs by up to 55% and 75%, respectively, while maintaining state-of-the-art performance in just a third of the training iterations. MOBIUS establishes a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.","short_abstract":"Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object detection and segmentation. However, their high computational cost limits adoption on resource-constrained platforms. We first examine the li...","url_abs":"https://arxiv.org/abs/2510.15026","url_pdf":"https://arxiv.org/pdf/2510.15026v1","authors":"[\"Mattia Segu\",\"Marta Tintore Gazulla\",\"Yongqin Xian\",\"Luc Van Gool\",\"Federico Tombari\"]","published":"2025-10-16T18:00:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}