Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2512.22760 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917172385677312 |
|---|---|
| author | Li, Yunge Xu, Lanyu |
| author_facet | Li, Yunge Xu, Lanyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22760 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers Li, Yunge Xu, Lanyu Computer Vision and Pattern Recognition 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. |
| title | Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.22760 |