Faster Vision Transformers with Adaptive Patches

ICLR 2026 Conference Submission10461 Authors

Keywords: efficient vision, vision transformers

TL;DR: We accelerate vision transformers by adaptively allocating different patch sizes within the same image, reducing the number of input tokens.

Abstract:

Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses this by using multiple different patch sizes within the same image. APT reduces the total number of input tokens by allocating larger patch sizes in more homogeneous areas and smaller patches in more complex ones.
APT achieves a drastic speedup in ViT inference and training, increasing throughput by 40\% on ViT-L and 50\% on ViT-H while maintaining downstream performance.
It can be applied to a previously fine-tuned ViT and converges in as little as 1 epoch.
It also significantly reduces training and inference time without loss of performance in high-resolution dense visual tasks, achieving up to 30\% faster training and inference in visual QA, object detection, and semantic segmentation.
We will release all code and trained models.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 10461