Efficiency Follows Global-Local Decoupling
Modern vision models must capture image-level context without sacrificing local detail while remaining computationally affordable. We revisit this tradeoff and advance a simple principle: decouple the roles of global reasoning and local representation. To operationalize this principle, we introduce ConvNeur, a two-branch architecture in which a lightweight neural memory branch aggregates global context on a compact set of tokens, and a locality-preserving branch extracts fine structure. A learned gate lets global cues modulate local features without entangling their objectives. This separation yields subquadratic scaling with image size, retains inductive priors associated with local processing, and reduces overhead relative to fully global attention. On standard classification, detection, and segmentation benchmarks, ConvNeur matches or surpasses comparable alternatives at similar or lower compute and offers favorable accuracy versus latency trade-offs at similar budgets. These results support the view that efficiency follows global-local decoupling.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
One Query, Many Scales: Sparse Mixture-of-Experts for Efficient Hierarchical Cross-View Geo-Localization
Cross-view geo-localization (CVGL) retrieves geo-tagged satellite imagery for a ground-view query. Most systems exhaustively search a flat, fixed-resolution gallery, incurring high cost over large areas and adapting poor…
Representation LearningDCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery
Causal discovery is critical for understanding complex data-generating mechanisms, yet traditional algorithms often struggle with highly non-linear and noisy systems, or suffer from severe computational bottlenecks. Rece…
Zero-shot GeneralizationCARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction
Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed in resource-constrained mobile devices, d…
Inductive BiasCD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. Despite the recent progress, it remains challenging to deal with heterogeneous data…
Federated LearningMedical Image AnalysisCD2-pFed: Cyclic Distillation-Guided Channel Decoupling for Model Personalization in Federated Learning
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. Despite the recent progress, it remains challenging to deal with heterogeneous …
Federated LearningMedical Image Analysis