Linear-Time Global Visual Modeling without Explicit Attention

TL;DR

This paper proposes a novel approach to global sequence modeling that replaces explicit attention with dynamically predicted parameters, achieving Transformer-level performance with linear complexity.

Contribution

It introduces a dynamic parameterization method that models global context without explicit attention, enabling efficient linear-time sequence modeling.

Findings

Dynamic parameterization can replace explicit attention in vision models.

The proposed method achieves comparable performance to Transformers.

Code is available at https://github.com/LeapLabTHU/WeightFormer.

Abstract

Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a novel perspective: we demonstrate that attention can be mathematically reframed as a Multi-Layer Perceptron (MLP) equipped with dynamically predicted parameters. Through this lens, we explain attention's global modeling power not as explicit token-wise aggregation, but as an implicit process where dynamically generated parameters act as a compressed representation of the global context. Inspired by this insight, we investigate a fundamental question: can we achieve Transformer-level sequence global modeling entirely through dynamic parameterization while maintaining linear complexity, effectively replacing explicit attention? To explore this, we design various dynamic parameter prediction strategies and integrate them into standard network layers. Extensive empirical studies on vision models demonstrate that dynamic parameterization can indeed serve as a highly effective, linear-complexity alternative to explicit attention, opening new pathways for efficient sequence modeling. Code is available at https://github.com/LeapLabTHU/WeightFormer.