Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers
This work addresses computational inefficiency in Vision Transformers for visual recognition tasks, offering incremental improvements in architectural optimization.
The paper tackled the problem of redundant token representations limiting computational efficiency in Vision Transformers by proposing neighbor-aware token reduction methods based on Hilbert curve reordering, achieving state-of-the-art accuracy-efficiency trade-offs.
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.