# SPoT: Subpixel Placement of Tokens in Vision Transformers

arXiv: https://arxiv.org/abs/2507.01654 · HTML: https://mlsanity.com/paper/2507.01654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer](https://mlsanity.com/paper/2303.17605/) (2023)
- [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number](https://mlsanity.com/paper/2406.09196/) (2024)
- [An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels](https://mlsanity.com/paper/2406.09415/) (2024)
- [PatchDropout: Economizing Vision Transformers Using Patch Dropout](https://mlsanity.com/paper/2208.07220/) (2022)
- [Subobject-level Image Tokenization](https://mlsanity.com/paper/2402.14327/) (2024)
- [Moving Off-the-Grid: Scene-Grounded Video Representations](https://mlsanity.com/paper/2411.05927/) (2024)
- [Mitigating the Bias of Centered Objects in Common Datasets](https://mlsanity.com/paper/2112.09195/) (2021)
- [A Spitting Image: Modular Superpixel Tokenization in Vision Transformers](https://mlsanity.com/paper/2408.07680/) (2024)
- [Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers](https://mlsanity.com/paper/2309.13353/) (2023)

## Abstract (arXiv)

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose Subpixel Placement of Tokens (SPoT), a novel tokenization strategy that positions tokens continuously within images, effectively sidestepping grid-based limitations. With our proposed oracle-guided search, we uncover substantial performance gains achievable with ideal subpixel token positioning, drastically reducing the number of tokens necessary for accurate predictions during inference. SPoT provides a new direction for flexible, efficient, and interpretable ViT architectures, redefining sparsity as a strategic advantage rather than an imposed limitation.