paper-with-me

Papers

Efficiency Follows Global-Local Decoupling

2026-03-20 · Zhenyu Yang, Gensheng Pei, Tao Chen, Yichao Zhou, Tianfei Zhou, Yazhou Yao, Fumin Shen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.19567

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

2026-08-02 · Ruijie Fan, Junyan Ye, Qi Zhu, Weijia Li arxiv

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 Learning

DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery

2026-06-19 · Zhengkang Guan, Yikang Chen, Yi He, Yunze Tong 외 arxiv

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 Generalization

CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction

2024-11-25 · CVPR 2025 1 · Yuan Zhou, Qingshan Xu, Jiequan Cui, Junbao Zhou 외

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 Bias

CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning

2022-04-08 · Yiqing Shen, Yuyin Zhou, Lequan Yu

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 Analysis

CD2-pFed: Cyclic Distillation-Guided Channel Decoupling for Model Personalization in Federated Learning

2022-01-01 · CVPR 2022 1 · Yiqing Shen, Yuyin Zhou, Lequan Yu

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