Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers

TL;DR

This paper introduces neighbor-aware token reduction methods for Vision Transformers using Hilbert curve reordering, improving computational efficiency while preserving local spatial context.

Contribution

It proposes novel neighbor-aware token pruning and merging strategies based on Hilbert curve reordering, enhancing efficiency without sacrificing accuracy.

Findings

Achieves state-of-the-art accuracy-efficiency trade-offs.

Explicitly preserves neighbor structure in token reduction.

Highlights importance of spatial continuity in ViT optimization.

Abstract

Vision Transformers (ViTs) have achieved remarkable success in visual recognition tasks, but redundant token representations limit their computational efficiency. Existing token merging and pruning strategies often overlook spatial continuity and neighbor relationships, resulting in the loss of local context. This paper proposes novel neighbor-aware token reduction methods based on Hilbert curve reordering, which explicitly preserves the neighbor structure in a 2D space using 1D sequential representations. Our method introduces two key strategies: Neighbor-Aware Pruning (NAP) for selective token retention and Merging by Adjacent Token similarity (MAT) for local token aggregation. Experiments demonstrate that our approach achieves state-of-the-art accuracy-efficiency trade-offs compared to existing methods. This work highlights the importance of spatial continuity and neighbor structure, offering new insights for the architectural optimization of ViTs.